System

Abstract

A system is provided.SOLUTION: A system, comprising: means for receiving a plurality of pieces of prompt information input by a user; means for analyzing the prompt information; means for selecting a generation algorithm based on a result of the analysis; means for generating a storyboard using the selected generation algorithm; means for returning the generated storyboard to the user; and means for displaying and editing the returned storyboard.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] The production of short videos is popular these days. However, while many users have ideas for videos, they do not understand specific filming methods or how to create storyboards. This makes it difficult for beginners and inexperienced users to create professional-quality videos. Furthermore, conventional methods require time and effort to create storyboards, hindering effective video production. To address these issues, the present invention provides a system that allows users to easily create specific storyboards. [Means for solving the problem]

[0005] The system of the present invention solves the above-mentioned problems by including a means for receiving multiple pieces of prompt information input by a user, a means for analyzing the prompt information, a means for selecting a generation algorithm based on the analysis results, a means for generating a storyboard using the selected generation algorithm, a means for returning the generated storyboard to the user, and a means for displaying and editing the returned storyboard. This allows the user to easily obtain a storyboard containing specific scene and action instructions, enabling efficient video production. The prompt information input by the user includes titles, scenes, actions, locations, etc., and the generation algorithm uses natural language processing and image generation technology.

[0006] A "user" is an entity that operates the system to input prompt information and generate a storyboard.

[0007] "Prompt information" is information that the user inputs into the system, and includes the title, scene, action, location, etc. of the video.

[0008] The "means for receiving" refers to a function for obtaining prompt information input by a user.

[0009] "Means for parsing" refers to the functionality for understanding the received prompt information and using it to select an appropriate generation algorithm.

[0010] A "generation algorithm" is a computer program for generating a storyboard based on input prompt information.

[0011] The "means for selecting" refers to a function for determining the generation algorithm to be used based on the analysis results.

[0012] A "storyboard" is a diagram or instruction manual that specifically shows the scenes and actions of a video, and serves as a guide for users when shooting a video.

[0013] "Means for returning" refers to a function for returning the generated storyboard to the user.

[0014] "Means for displaying and editing" refers to a function that allows a user to visually check the storyboard and make corrections as necessary.

[0015] A "title" is a word or phrase that succinctly describes the subject of the video.

[0016] A "scene" refers to a specific situation or situation in a video, and is divided based on time and location.

[0017] "Action" refers to the specific actions that characters and objects take in a scene.

[0018] "Location" refers to the physical or virtual place where a scene is set.

[0019] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0020] "Image generation technology" is a technology that allows computers to generate images from text or other data. [Brief explanation of the drawings]

[0021] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6]FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0022] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0023] First, the terms used in the following description will be explained.

[0024] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0025] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0026] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0027] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0028] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0032] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0033] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0034] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0035] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0036] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0039] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0040] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0041] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0042] The present invention relates to a system for automatically generating storyboards based on prompt information entered by a user. The following describes the program processing and specific examples of the system.

[0043] System configuration and operation

[0044] 1. User enters prompt

[0045] The user launches the application on their device (e.g., PC or smartphone) and logs in. They click the "Create a new project" button and fill out a form to enter prompt information (title, scene, action, location, etc.) based on their video idea.

[0046] 2. Sending prompt information

[0047] The terminal collects the prompt information input by the user, generates an API request to transmit the information to the server, and transmits the request to the server.

[0048] 3. Parsing prompt information

[0049] The server analyzes the received prompt information, understands the content using natural language processing technology, and then selects the optimal generation algorithm (e.g., GPT-3 or image generation technology) based on the prompt information.

[0050] 4. Storyboard generation

[0051] The server uses a selected generation algorithm to generate a storyboard based on the prompt information, which contains specific instructions for each scene and action in the video.

[0052] 5. Returning the storyboard

[0053] The server sends the generated storyboard back to the user's device as an API response, and the device analyzes the received data and displays it on the user interface.

[0054] 6. User Review and Editing

[0055] The user can check the storyboard displayed on the terminal and make edits as necessary. Once the storyboard has been edited, the user can confirm it by clicking the final confirmation button.

[0056] Specific examples

[0057] For example, let's say a user wants to create a short comedy video about a clumsy friend trying to give something they forgot in the school hallway. The user would enter the prompt information as follows:

[0058] Title: "Forgotten Things"

[0059] Scene: School hallway

[0060] Action: Handing something back to a friend, making a mistake

[0061] Location: School hallway

[0062] The device sends these prompts to the server, which analyzes the information and selects an appropriate generation algorithm. The generation algorithm generates a storyboard, and the output is a storyboard containing the following scenes:

[0063] 1. Scene 1: In the school hallway, a friend comes running with something they forgot.

[0064] 2. Scene 2: Your friend slips and falls.

[0065] 3. Scene 3: The friend laughs and hands over the forgotten item.

[0066] The storyboard is sent back to the device from the server, where the user can review and edit it. For example, the user can add details about "why the friend fell" in Scene 2. Finally, the storyboard is finalized to the user's satisfaction, and the video is shot based on it.

[0067] In this way, the system of the present invention allows users to easily create specific storyboards and efficiently proceed with professional video production.

[0068] The processing flow will be explained below.

[0069] Step 1: User enters prompt information

[0070] The user starts the application on the terminal and logs in.

[0071] The user clicks the "Create a new project" button, which displays a form for entering prompt information.

[0072] The user enters information such as title, scene, action, location, etc. into the input fields and clicks the "Submit" button.

[0073] Step 2: The device sends the prompt information to the server

[0074] The terminal collects the prompt information entered by the user.

[0075] The device generates an API request to send the collected prompt information to the server.

[0076] The device executes an API request and sends the prompt information to the server.

[0077] Step 3: The server parses the prompt information

[0078] The server uses natural language processing techniques to parse the received prompt information.

[0079] The server interprets the contents of the prompt information and selects a generation algorithm based on the analysis results.

[0080] Step 4: The server generates the storyboard using a generation algorithm

[0081] The server generates the storyboard using a selected generation algorithm (e.g., GPT-3 or image generation technology).

[0082] Based on the prompt information, the server creates a storyboard containing specific instructions for each scene and action.

[0083] Step 5: The server sends the generated storyboard back to the device

[0084] The server prepares an API response to send the generated storyboard to the user's device.

[0085] The server executes the API response and sends the storyboard to the device.

[0086] Step 6: The device displays the storyboard, and the user checks and edits it.

[0087] The terminal analyzes the received storyboard data and displays it on the user interface.

[0088] The user can check the displayed storyboard and edit each scene and action as necessary.

[0089] When the user has finished editing, he clicks the "Save" button.

[0090] Step 7: The device sends the edited storyboard to the server

[0091] The device generates an API request to send the storyboard that the user has edited and confirmed to the server.

[0092] The device executes an API request and sends the edited storyboard to the server.

[0093] Step 8: The server saves the final storyboard and notifies you that the confirmation is complete

[0094] The server stores the received final storyboard data in a database.

[0095] The server prepares an API response to notify the device that the final storyboard has been confirmed.

[0096] The server executes the API response and sends a confirmation completion notification to the terminal.

[0097] By following the steps above, users can efficiently generate concrete storyboards and use them as a guide for video production.

[0098] Example 1

[0099] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0100] In conventional video production, creating storyboards requires specialized knowledge and effort, making it difficult for beginners and general users. Furthermore, creating storyboards manually takes time and effort, hindering efficient video production. Therefore, there has been a demand for a system that allows users to easily and efficiently create and edit storyboards.

[0101] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0102] In this invention, the server includes means for transmitting prompt information from the user's terminal to the server, means for the server to analyze the prompt information using natural language processing technology, and means for the server to select an optimal generation algorithm using the natural language processing technology. This makes it possible to efficiently generate a specific storyboard based on the prompt information entered by the user and return the storyboard to the user.

[0103] "Prompt information" is information that a user inputs based on an idea for a video, and includes details such as title, scenes, actions, and locations.

[0104] The "means for analyzing" is a function for understanding and analyzing the content of the prompt information received by the server using natural language processing technology.

[0105] The "generation algorithm" is an algorithm used to generate a storyboard based on prompt information, and specifically includes natural language processing technology and image generation technology.

[0106] A "storyboard" is a visual sketch or depiction that contains specific instructions for each scene or action in a video.

[0107] The "means for returning" is a function for returning the storyboard generated by the server to the user's device, and is performed as an API response.

[0108] The "display and editing means" refers to an interface and functionality that allows the received storyboard to be displayed on the user terminal and for the user to edit it as needed.

[0109] "Natural language processing technology" is a technology that enables computers to understand and analyze human language, and is used to select generation algorithms and analyze prompt information.

[0110] "Image generation technology" refers to technology that allows a computer to generate images based on prompt information, creating a concrete visual depiction of the storyboard.

[0111] An "API request" is a communication request from a user terminal to a server to request the operation of a specific service, and is used when sending prompt information.

[0112] An "API response" is response data returned from the server to the user terminal, and includes the generated storyboard.

[0113] The present invention relates to a system for automatically generating storyboards based on prompt information entered by a user. The program processing of the system and an embodiment thereof will be specifically described below.

[0114] System configuration

[0115] The system uses user terminals, servers, and API requests and responses to communicate between them.

[0116] 1. User enters prompt

[0117] The user launches the application on their device (such as a PC or smartphone) and logs in. After logging in, the user clicks the "Create a new project" button and enters information into a form for entering prompt information (such as title, scene, action, location, etc.). This prompt information is used to generate a storyboard.

[0118] Software used: Web application, mobile application

[0119] 2. Sending prompt information

[0120] The terminal collects the prompt information entered by the user and generates an API request as JSON formatted data, which is then sent to the server using the HTTP POST method.

[0121] Technologies used: RESTful API, JSON data format

[0122] 3. Parsing prompt information

[0123] The server analyzes the received prompt information using natural language processing technology. Specifically, it uses a natural language processing engine (e.g., NLTK or Spacy) to analyze the prompt information and understand its content. Based on the analysis results, it selects the optimal generation algorithm (e.g., the generative AI model GPT-3 or image generation technology).

[0124] Software used: NLTK, Spacy, GPT-3

[0125] 4. Storyboard generation

[0126] The server uses the selected generation algorithm to generate a storyboard based on the prompt information. Specifically, it uses GPT-3 to generate detailed scene descriptions and image generation technology to create specific scene images. These are then combined to create the storyboard.

[0127] Technologies used: GPT-3, image generation technology

[0128] 5. Returning the storyboard

[0129] The server returns the generated storyboard to the user's device as an API response, which is also in JSON format.

[0130] Technologies used: RESTful API, JSON data format

[0131] 6. User Review and Editing

[0132] The user can check the storyboard displayed on the terminal and make edits as necessary. Once editing is complete, the user clicks the final confirmation button to finalize the storyboard.

[0133] Software used: Web application, mobile application

[0134] Specific examples

[0135] As an example, suppose a user wants to create a short comedy video about "making a mistake while trying to give something to a friend in the school hallway."

[0136] Example of user prompt input

[0137] Title: "Forgotten Things"

[0138] Scene: School hallway

[0139] Action: Handing something back to a friend, making a mistake

[0140] Location: School hallway

[0141] The user inputs this information into the application, and the device sends it to the server. The server analyzes the information and selects an appropriate generation algorithm. The generation algorithm generates a storyboard containing the following scenes:

[0142] 1. Scene 1: In the school hallway, a friend comes running with something they forgot.

[0143] 2. Scene 2: Your friend slips and falls.

[0144] 3. Scene 3: The friend laughs and hands over the forgotten item.

[0145] The server sends the storyboard back to the device, where the user can review and edit it. For example, the user can add details about "why the friend fell" in Scene 2.

[0146] In this way, the system of the present invention enables efficient video production by allowing users to easily create and edit specific storyboards.

[0147] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0148] Step 1: User Enters Prompt

[0149] The user launches the application on their device (PC, smartphone, etc.) and logs in. After logging in, they click the "Create a new project" button and enter the prompt information (title, scene, action, location, etc.) in the form.

[0150] Input: Prompt information entered by the user (title, scene, action, location)

[0151] Output: The prompt information entered is saved in the form

[0152] Specific behavior:

[0153] Start the application and enter your user ID and password in the login form.

[0154] After logging in, on the dashboard screen, click the "Create a new project" button.

[0155] In the form that appears, enter the title "Forgotten Item," the scene "School Hallway," the action "Giving forgotten item to friend, making a mistake," and the location "School Hallway."

[0156] Step 2: Send prompt information

[0157] The terminal collects the prompt information entered by the user and generates an API request, which is then sent to the server using the HTTP POST method.

[0158] Input: The prompt information entered by the user.

[0159] Output: The generated API request is sent to the server.

[0160] Specific behavior:

[0161] Collect prompt information as JSON format data and generate an API request.

[0162] Send an API request to the server using the HTTP POST method.

[0163] Wait for a response from the server.

[0164] Step 3: Parse prompt information

[0165] The server analyzes the received prompt information using natural language processing technology. Specifically, it uses a natural language processing engine (such as NLTK or Spacy) to analyze the prompt information and understand its content.

[0166] Input: Received prompt information

[0167] Output: Analysis results (understanding the contents of prompt information)

[0168] Specific behavior:

[0169] The server receives the API request.

[0170] The received prompt information is analyzed using a natural language processing engine.

[0171] As a result of the analysis, data that understands the content of the prompt information is generated.

[0172] Step 4: Selecting a generation algorithm

[0173] The server selects the optimal generation algorithm (e.g., GPT-3 or image generation technology) based on the analysis results.

[0174] Input: Analysis result of prompt information

[0175] Output: The selected generation algorithm

[0176] Specific behavior:

[0177] Based on the analysis results of the prompt information, candidate generation algorithms are evaluated.

[0178] The most suitable algorithm is selected from among those such as GPT-3 and image generation technology.

[0179] Record the selected generation algorithm.

[0180] Step 5: Generate the storyboard

[0181] The server uses the selected generation algorithm to generate a storyboard based on the prompt information. Specifically, it uses GPT-3 to generate detailed scene descriptions and image generation technology to create specific scene images. These are then combined to create the storyboard.

[0182] Input: Selected generation algorithm, prompt information

[0183] Output: Generated storyboard

[0184] Specific behavior:

[0185] Use GPT-3 to generate detailed scene descriptions based on prompt information.

[0186] Image generation techniques are used to create concrete scene images based on scene descriptions.

[0187] Integrate the scene description with the generated images to build a complete storyboard.

[0188] Step 6: Return the storyboard

[0189] The server returns the generated storyboard to the user's device as an API response, which is also in JSON format.

[0190] Input: Generated storyboard

[0191] Output: Storyboard data as API response

[0192] Specific behavior:

[0193] Convert the generated storyboard into JSON format.

[0194] As an API response, the storyboard is returned to the device in an HTTP response message.

[0195] Step 7: User review and editing

[0196] The user checks the storyboard displayed on the terminal and makes edits as necessary. Once editing is complete, the user clicks the final confirmation button to finalize the storyboard.

[0197] Input: Returned storyboard

[0198] Output: Finalized storyboard

[0199] Specific behavior:

[0200] Check the storyboard on the device's UI.

[0201] Add details or modify scenes and actions as needed.

[0202] Once you're done editing, click the "Final Confirm" button to finalize the storyboard.

[0203] (Application example 1)

[0204] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0205] Conventional storyboard generation systems can automatically generate storyboards based on prompt information entered by the user, but they have limited means for sharing the generated storyboards with other users. Furthermore, they lack an interface or means for users to easily edit the storyboards they generate and use them to create videos. Therefore, there is a need for a system that allows users to efficiently share generated storyboards and easily edit and use them.

[0206] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0207] In this invention, the server includes means for receiving a plurality of pieces of prompt information input by a user, means for analyzing the prompt information, means for selecting a generation algorithm based on the analysis result, means for generating a storyboard using the selected generation algorithm, means for returning the generated storyboard to the user, means for displaying and editing the returned storyboard, and means for sharing the generated storyboard with other users via a content sharing service. This enables users to efficiently share the generated storyboard with other users and use it for editing or video production.

[0208] "Prompt information" refers to information that a user inputs to generate a storyboard, specifically, titles, scenes, actions, and locations.

[0209] A "generation algorithm" is an algorithm that analyzes input prompt information and generates content such as storyboards based on that information, and primarily includes natural language processing technology and image generation technology.

[0210] A "storyboard" is a visual illustration that shows the elements and movements of each scene in order to plan and execute video production.

[0211] The "content sharing service" refers to a service via the Internet for sharing content such as created storyboards with other users.

[0212] "Parsing" refers to the process of understanding the input prompt information and selecting an appropriate generation algorithm.

[0213] "User" refers to a person or organization that uses the storyboard generation system.

[0214] This invention relates to a system that automatically generates storyboards based on prompt information entered by users, and allows them to be shared and edited. The system's program uses the Python language, Flask (a web framework), and the OpenAI API. The user's smartphone functions as the terminal, and the server is the backend that processes requests from users.

[0215] System configuration and operation

[0216] 1. User enters prompt

[0217] The user launches the smartphone application and logs in. The user presses a button to create a new project and fills in a form to enter prompt information based on the video idea. The prompt information includes the title, scene, action, and location. This information is sent from the user's device to the server.

[0218] 2. Parsing prompt information

[0219] The server receives the prompt information entered by the user and analyzes the content using natural language processing technology. Specifically, it uses a generative AI model such as OpenAI's GPT-3 to understand the meaning of the prompt information and select an appropriate generation algorithm.

[0220] 3. Storyboard generation

[0221] The server uses the selected generation algorithm to generate a storyboard based on the prompt information, which contains specific instructions for each scene and action in the video.

[0222] 4. Return and display of storyboards

[0223] The server returns the generated storyboard to the user's device, which receives the data returned as an API response and displays it on the user interface.

[0224] 5. User Editing and Sharing

[0225] The user can check the storyboard displayed on the device and edit it as necessary. Once edited, the storyboard can be shared with other users via a content sharing service.

[0226] Hardware and software used

[0227] Hardware: Smartphone (terminal) and server

[0228] Software: Python (programming language), Flask (web framework), OpenAI API (generative AI model)

[0229] Specific examples

[0230] For example, if a user enters the video idea "Morning yoga by a tranquil lake with a sunrise in the background" as a prompt, they would enter the following information:

[0231] Title: "Morning Yoga"

[0232] Scene: A calm lake with a sunrise in the background

[0233] Movement: Yoga pose

[0234] This prompt information is sent to the server in the following format:

[0235] Generate a storyboard: Title: "Morning Yoga", Scene: Calm lake with sunrise in the background, Action: Striking a yoga pose

[0236] The server parses this information and generates a storyboard like this:

[0237] 1. Scene 1: The sun begins to rise, revealing a tranquil scene over a lake.

[0238] 2. Scene 2: The protagonist lays out her yoga mat and begins getting ready.

[0239] 3. Scene 3: She is shown performing a yoga pose.

[0240] The generated storyboard is returned to the user and displayed on their device, where the user can edit it as needed and ultimately share it with other users via a content sharing service.

[0241] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0242] Step 1:

[0243] The user launches the smartphone application and logs in. They press the "Create a new project" button and fill out a form to enter prompt information based on their video idea. This information includes the title, scene, action, and location. The entered prompt information is temporarily saved on the device.

[0244] input:

[0245] Prompt information for user input (title, scene, action, location)

[0246] output:

[0247] Prompt information stored on the device

[0248] Step 2:

[0249] The device generates an API request to send the saved prompt information to the server and sends it to the server.

[0250] input:

[0251] Prompt information stored on the device

[0252] output:

[0253] API requests sent to the server

[0254] Step 3:

[0255] The server receives the API request and analyzes the sent prompt information. Using natural language processing technology, such as OpenAI's API, the server understands the content of the prompt information and selects the appropriate generation algorithm.

[0256] input:

[0257] API requests sent to the server

[0258] output:

[0259] Prompt information analysis results

[0260] Selected generation algorithm

[0261] Step 4:

[0262] The server uses a selected generation algorithm to generate a storyboard based on the prompt information, which contains specific instructions for each scene and action in the video.

[0263] input:

[0264] Prompt information analysis results

[0265] Selected generation algorithm

[0266] output:

[0267] Generated storyboard

[0268] Step 5:

[0269] The server sends the generated storyboard back to the user's device as an API response, and the device analyzes the received data and displays it on the user interface.

[0270] input:

[0271] Generated storyboard

[0272] output:

[0273] API response sent back to the device

[0274] Storyboard display on device

[0275] Step 6:

[0276] The user can check the storyboard displayed on the device and make edits as necessary. Once editing is complete, the storyboard is confirmed by pressing the final confirmation button.

[0277] input:

[0278] Storyboard displayed on the device

[0279] output:

[0280] User edited storyboard

[0281] Step 7:

[0282] The finalized storyboard can be shared with other users via a content sharing service. The server receives the share request and provides a share link to other users.

[0283] input:

[0284] Storyboard confirmed by user

[0285] output:

[0286] Storyboards shared through content sharing services

[0287] Shared link provided to other users

[0288] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0289] The present invention relates to a system that combines prompt information input by a user with an emotion engine that recognizes the user's emotions. Below, the processing of the system program and specific examples will be described.

[0290] System configuration and operation

[0291] 1. User enters prompt

[0292] The user launches the application on their device (e.g., PC or smartphone) and logs in. They click the "Create a new project" button and fill out a form to enter prompt information (title, scene, action, location, etc.) based on their video idea.

[0293] 2. Emotion recognition by emotion engine

[0294] The terminal operates an emotion engine that recognizes emotions from the user's facial expressions, voice, and input text while the user is entering prompt information. The emotion engine analyzes the user's current emotional state and transmits the results to the server.

[0295] 3. Sending prompt and emotional information

[0296] The terminal collects prompt information input by the user, generates an API request to be sent to the server together with emotion information obtained from the emotion engine, and sends the request to the server.

[0297] 4. Analysis of prompt information and emotional information

[0298] The server analyzes the received prompt and emotional information, understands the content using natural language processing and facial expression analysis technologies, and then selects the optimal generation algorithm (e.g., GPT-3 or image generation technology) based on the prompt and emotional information.

[0299] 5. Storyboard Generation

[0300] The server uses the selected generation algorithm to generate a storyboard based on the prompt information and the emotion information, which includes specific instructions for each scene and action in the video and elements that reflect the user's emotional state.

[0301] 6. Returning the storyboard

[0302] The server sends the generated storyboard back to the user's device as an API response, and the device analyzes the received data and displays it on the user interface.

[0303] 7. User Review and Editing

[0304] The user can check the storyboard displayed on the terminal and make edits as necessary. Once the storyboard has been edited, the user can confirm it by clicking the final confirmation button.

[0305] Specific examples

[0306] For example, let's say a user wants to create a short comedy video about a clumsy friend trying to give something they forgot in the school hallway. The user would enter the prompt information as follows:

[0307] Title: "Forgotten Things"

[0308] Scene: School hallway

[0309] Action: Handing something back to a friend, making a mistake

[0310] Location: School hallway

[0311] At the same time, the emotion engine analyzes the user's facial expressions and voice while inputting and recognizes that the user is in a happy emotional state. The device then transmits this prompt information and emotion information to the server.

[0312] The server analyzes the information and selects the appropriate generation algorithm, which generates the storyboard and outputs a storyboard containing the following scenes:

[0313] 1. Scene 1: In the school hallway, a friend comes running with something they forgot. They look happy.

[0314] 2. Scene 2: A friend slips and falls. Happy expressions and actions.

[0315] 3. Scene 3: The friend laughs and hands over the forgotten item.

[0316] The server sends the storyboard back to the device, where the user can review and edit it. For example, the user can add details about "why the friend fell" in Scene 2. Finally, once the user is satisfied with the storyboard, the video is shot.

[0317] In this way, the system of the present invention allows the user to easily create specific storyboards and efficiently proceed with the production of professional videos that reflect the user's emotions.

[0318] The processing flow will be explained below.

[0319] Step 1: User enters prompt information

[0320] The user starts the application on the terminal and logs in.

[0321] The user clicks the "Create a new project" button, which displays a form for entering prompt information.

[0322] The user enters information such as title, scene, action, location, etc. into the input fields and clicks the "Submit" button.

[0323] Step 2: The device activates the emotion engine

[0324] The terminal runs the emotion engine while the user is entering the prompt information.

[0325] The emotion engine uses a camera and microphone to analyze the user's facial expressions and voice in real time.

[0326] Step 3: The device sends prompt information and emotion information to the server.

[0327] The terminal collects the prompt information input by the user and combines it with the emotion information obtained from the emotion engine into one data packet.

[0328] The device generates an API request for transmitting the collected prompt information and emotion information to the server, and sends the request to the server.

[0329] Step 4: The server analyzes the prompt and emotion information

[0330] The server analyzes the received prompt information and emotion information.

[0331] The server uses natural language processing technology to analyze the content of the prompt information and uses the emotional information to understand the user's emotional state.

[0332] Based on the analysis results, the server selects the optimal generation algorithm based on prompt information and emotion information.

[0333] Step 5: The server generates the storyboard using a generation algorithm

[0334] The server uses a selected generation algorithm (e.g., GPT-3 or image generation technology) to generate a storyboard based on prompt information and emotion information.

[0335] The server creates a storyboard containing specific instructions for each scene and action, as well as elements that reflect the user's emotional state.

[0336] Step 6: The server sends the generated storyboard back to the device

[0337] The server prepares an API response to return the generated storyboard to the user's device.

[0338] The server executes the API response and sends the storyboard to the device.

[0339] Step 7: The device displays the storyboard, and the user checks and edits it.

[0340] The terminal analyzes the received storyboard data and displays it on the user interface.

[0341] The user checks the displayed storyboard and confirms the content of each scene and action.

[0342] The user edits the storyboard as needed and clicks the "Save" button.

[0343] Step 8: The device sends the edited storyboard to the server

[0344] The device generates an API request to send the storyboard that the user has edited and confirmed to the server.

[0345] The device executes an API request and sends the edited storyboard to the server.

[0346] Step 9: The server saves the final storyboard and notifies you that the confirmation is complete

[0347] The server stores the received final storyboard data in a database.

[0348] The server prepares an API response to notify the device that the final storyboard has been confirmed.

[0349] The server executes the API response and sends a confirmation completion notification to the terminal.

[0350] Through the above steps, users can efficiently create detailed storyboards and proceed with the production of professional videos that reflect emotions.

[0351] Example 2

[0352] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0353] Conventional storyboard generation systems have difficulty reflecting user emotions, and because they generate content based solely on prompt information, they lack the subtle nuances and emotional expression desired by users. Furthermore, users sometimes find it difficult to clearly communicate their emotions, which can result in generated content that deviates from the user's intentions. Therefore, there has been a demand for a system that generates storyboards that effectively reflect user emotions.

[0354] The specification processing by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving a plurality of pieces of prompt information input by the user, means for analyzing the prompt information, means for selecting a generation algorithm based on the analysis result, means for generating a storyboard using the selected generation algorithm, means for returning the generated storyboard to the user, means for displaying and editing the returned storyboard, means for detecting the user's emotions and analyzing the emotion information together with the prompt information, and means for including emotion-reflecting elements in a storyboard generated based on the analyzed emotion information. This makes it possible to generate a storyboard that reflects the user's emotions.

[0355] "Prompt information" is information based on the idea of ​​the video, such as title, scene, action, location, etc., entered by the user.

[0356] An "emotion engine" is software that detects emotions by analyzing a user's facial expressions, voice, input text, etc.

[0357] A "generation algorithm" is an algorithm used to generate a storyboard or the like based on prompt information and emotion information.

[0358] A "storyboard" is a visual storyboard that contains specific instructions for each scene and action in a video, as well as elements that reflect the user's emotional state.

[0359] The "server" is a computer system that analyzes prompt information and emotional information, selects a generation algorithm based on that information, generates a storyboard, and returns it to the terminal.

[0360] A "terminal" is a device, such as a personal computer or smartphone, through which a user inputs prompt information and checks and edits the generated storyboard.

[0361] "Analysis means" refers to a method or function for understanding received prompt information and emotion information and performing processing based on that information.

[0362] "Emotion-reflecting elements" are elements that are reflected in the storyboard based on the user's emotional information, and include, for example, the facial expressions and movements of characters.

[0363] "Natural language processing" is the technology that enables computers to understand and generate human language.

[0364] "Image generation technology" is a technology that allows computers to generate visual content.

[0365] The present invention relates to a system that combines prompt information input by a user with an emotion engine that recognizes the user's emotions. Below, the processing of the system program and specific examples will be described.

[0366] System configuration and operation

[0367] This system consists of three main components: the user, the device, and the server. The user inputs prompt information using the device, and the device analyzes the user's emotions using an emotion engine. The analyzed prompt information and emotion information are sent to the server, which then generates a storyboard based on this and sends it back to the device.

[0368] 1. User enters prompt

[0369] A user launches the application on a device (such as a PC or smartphone) and logs in. The user clicks the "Create a new project" button and enters prompt information based on their video idea, including title, scene, action, location, etc.

[0370] 2. Emotion recognition by emotion engine

[0371] The device activates an emotion engine to analyze the user's facial expressions, voice, and input text to determine their emotions. This emotion information reflects the user's current emotional state and is temporarily stored on the device along with the prompt information.

[0372] 3. Sending prompt and emotional information

[0373] The device sends the prompt information entered by the user and the emotion information analyzed by the emotion engine to the server via an API request.

[0374] 4. Analysis of prompt information and emotional information

[0375] The server analyzes the received prompt information and emotional information. Specifically, it uses natural language processing technology (e.g., GPT-3) and facial expression analysis technology to understand the content and emotion of the prompt. Based on the analysis results, it selects the optimal generation algorithm.

[0376] 5. Storyboard Generation

[0377] The server uses the selected generation algorithm to generate a storyboard based on the prompt information and the emotion information, which includes specific instructions for each scene and elements that reflect the user's emotional state.

[0378] 6. Returning the storyboard

[0379] The server returns the generated storyboard to the device as an API response, and the device displays the received storyboard on the user interface for the user to confirm.

[0380] 7. User Review and Editing

[0381] The user checks the displayed storyboard and makes edits as necessary. Once editing is complete, the user clicks the "Final Confirm" button to finalize the storyboard.

[0382] Specific examples

[0383] For example, let's say a user wants to create a short comedy video about "making a mistake while trying to give something to a friend in the school hallway." The user would enter the prompt information as follows:

[0384] Title: "Forgotten Things"

[0385] Scene: School hallway

[0386] Action: Handing something back to a friend, making a mistake

[0387] Location: School hallway

[0388] At the same time, the emotion engine analyzes the user's facial expressions and voice while inputting and recognizes that the user is in a happy emotional state. The device then transmits this prompt information and emotion information to the server.

[0389] The server analyzes the information and selects the appropriate generation algorithm, which generates a storyboard containing the following scenes:

[0390] 1. Scene 1: In the school hallway, a friend comes running with something they forgot. They look happy.

[0391] 2. Scene 2: A friend slips and falls. Happy expressions and actions.

[0392] 3. Scene 3: The friend laughs and hands over the forgotten item.

[0393] The server sends the storyboard back to the device, where the user can review and edit it. For example, the user can add details about "why the friend fell" in Scene 2. Finally, once the user is satisfied with the storyboard, the video is shot.

[0394] In this way, the system allows users to easily create specific storyboards and efficiently create professional videos that reflect the user's emotions.

[0395] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0396] Step 1:

[0397] The user launches the application on the terminal and logs in.

[0398] Input: User login information (username, password).

[0399] How it works: A user goes to a terminal, opens an application, and enters their username and password into the login form.

[0400] Output: The application dashboard screen is displayed.

[0401] Step 2:

[0402] User clicks the "Create a new project" button and fills in prompt information based on their video idea.

[0403] Input: Prompt information (title, scene, action, location).

[0404] Action: The user writes down their video idea in a form where they enter prompt information. For example, "Title: Lost Item, Scene: School Hallway, Action: Handing Over Lost Item to Friend, Making a Mistake, Location: School Hallway."

[0405] Output: The entered prompt information is temporarily saved on the terminal.

[0406] Step 3:

[0407] The device activates an emotion engine and analyzes emotions from the user's facial expressions, voice, and input text.

[0408] Input: User's facial expression data, voice data, input text.

[0409] How it works: The device uses a camera and microphone to record the user's facial expressions and voice, which are then analyzed by the emotion engine. For example, if the user is laughing happily, the emotion engine will detect "happiness."

[0410] Output: Generate emotional information (e.g., enjoyment) and temporarily store it on the device.

[0411] Step 4:

[0412] The terminal transmits prompt information and emotion information to the server.

[0413] Input: prompt information, emotion information.

[0414] How it works: The device collects this information, converts it into JSON format, and sends it to the server as an API request.

[0415] Output: The server receives the prompt information and emotion information.

[0416] Step 5:

[0417] The server analyzes the received prompt information and emotion information.

[0418] Input: Received prompt information, emotion information.

[0419] How it works: The server uses natural language processing technology (such as GPT-3) and facial expression analysis technology to analyze the content and sentiment of the prompt.

[0420] Output: Based on the analysis results, the optimal generative algorithm is selected (e.g., GPT-3 model).

[0421] Step 6:

[0422] The server uses a selected generation algorithm to generate a storyboard based on the prompt information and the emotion information.

[0423] Input: Parsed prompt information, sentiment information, selected generation algorithm.

[0424] How it works: The server uses GPT-3 to automatically generate a storyboard, for example, a storyboard containing scenes such as "Scene 1: School hallway, a friend comes running with something they forgot. Happy expression."

[0425] Output: Storyboard data is generated.

[0426] Step 7:

[0427] The server returns the generated storyboard to the terminal.

[0428] Input: The generated storyboard data.

[0429] Operation: The server sends the storyboard data to the device as an API response.

[0430] Output: The device receives the storyboard data.

[0431] Step 8:

[0432] The terminal displays the received storyboard on the user interface and allows the user to check it.

[0433] Input: Received storyboard data.

[0434] Action: The device parses the received data and displays it in its interface for the user to review.

[0435] Output: The generated storyboard is displayed to the user.

[0436] Step 9:

[0437] The user checks the displayed storyboard and makes edits as necessary.

[0438] Input: The displayed storyboard.

[0439] Action: The user edits the storyboard using a tablet pen or mouse. For example, adding "Why did my friend fall down?" in Scene 2. Once editing is complete, the user clicks the "Final Confirm" button to finalize the storyboard.

[0440] Output: Edited and finalized storyboard.

[0441] (Application example 2)

[0442] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0443] In modern society, users' meal choices vary greatly depending on their mood and emotions on that day. However, conventional food delivery services lack the ability to recommend dishes that take the user's emotional state into account. As a result, it is difficult for users to achieve sufficient satisfaction when choosing a meal. In particular, there is a need for food recommendations that accurately reflect the user's emotions.

[0444] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0445] In this invention, the server includes means for receiving a plurality of pieces of prompt information input by the user, means for analyzing the prompt information and emotion data, means for selecting a generation algorithm based on the analysis results, means for analyzing the emotion information obtained from the emotion engine, means for recommending an optimal dish based on the prompt information and emotion information, and means for returning the recommended dish to the user, thereby enabling recipe suggestions that comprehensively consider the user's emotional state.

[0446] "User-entered prompt information" refers to a number of pieces of information entered by a user to embody a specific request or idea, including title, scene, action, location, food request, etc.

[0447] "Means for analyzing prompt information" refers to a processing function for analyzing the input prompt information in detail and understanding the user's intentions and goals.

[0448] The "means for selecting a generation algorithm" is a processing mechanism for determining an optimal generation algorithm based on the analyzed prompt information and emotion data.

[0449] The "means for generating a storyboard using a selected generation algorithm" is a function that uses a selected generation algorithm to automatically generate a storyboard that serves as a blueprint for a video or image.

[0450] The "means for returning the generated storyboard to the user" is a means for transmitting the generated storyboard to the user's terminal so that it can be displayed and edited.

[0451] "Means for displaying and editing the returned storyboard" refers to a function that allows the user to display the received storyboard on the terminal and edit or modify it as necessary.

[0452] The "emotion engine" is an analysis engine that analyzes the user's voice data, text data, and facial expression image data to identify the user's current emotional state.

[0453] "Means for integrating emotional information into analysis results" refers to a function that combines emotional information obtained from the emotion engine with the analysis results of prompt information to achieve comprehensive understanding.

[0454] The "means for recommending the most suitable dish" is a function for suggesting a dish that matches the user's emotional state and request based on the analyzed prompt information and emotional information.

[0455] The "means for returning recommended dishes to the user" refers to a means for sending information about the selected dishes to the user's terminal and suggesting them to the user.

[0456] The present invention relates to a food delivery application that recommends dishes taking into account the emotional state of the user. Specific embodiments for implementing the present invention will be described below.

[0457] System configuration

[0458] This system consists of an application that runs on the user's device, such as a smartphone or PC, and an emotion engine and generation algorithm that runs on the server side.

[0459] procedure

[0460] 1. User enters prompt

[0461] The user launches the application and enters their meal preference as a prompt, for example, a request such as "I would like something light."

[0462] 2. Emotion recognition by emotion engine

[0463] The device collects the user's voice data, text data, and facial expression image data when prompting, and sends them to the emotion engine, which analyzes this data and identifies the user's current emotional state.

[0464] 3. Sending prompt and emotional information

[0465] The device sends the prompt information and analyzed emotion data to the server, which then selects a generation algorithm based on this information.

[0466] 4. Food Recommendations

[0467] The server-side algorithm analyzes prompt and emotion information to recommend the most suitable dish. For example, if a user feels tired and wants to refresh, it will recommend cold soba noodles or a refreshing salad.

[0468] 5. Returning Recommendations

[0469] The server returns recommended dish information to the user's terminal, and the user can order dishes based on this information.

[0470] Hardware and software used

[0471] Hardware: Smartphones, PCs

[0472] Software: Sentiment analysis API (Python library), food delivery API

[0473] Data format: JSON format, text data, audio data, image data

[0474] Specific examples

[0475] For example, consider a case where a user feels tired and wants to relax. The user inputs into the app, "I'm tired, I want to relax. I want to eat something refreshing." The emotion engine analyzes the user's voice and facial expressions to determine that the user wants to relax. Based on the results of the analysis on the server side, recommendations such as "cold soba noodles" or "refreshing salad" are sent back to the user.

[0476] This allows users to easily order the food that best suits their emotional state at the time.

[0477] Examples of prompt statements include "I would like to eat something light," "I would like some spicy Chinese food," and "I would like to eat a special dessert."

[0478] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0479] Step 1:

[0480] A user launches the application and inputs a desired dish as a prompt. For example, the user may input "I want something light." The prompt information input by the user is collected in an input field of the application. The input data includes the user's request.

[0481] Step 2:

[0482] The device collects the user's voice data, text data, and facial expression image data. It prepares to send this data to the emotion engine. The collected data includes voice files (e.g., "I'm tired, I want to calm down"), text data, and image files (user's facial expressions).

[0483] Step 3:

[0484] The emotion engine analyzes the collected voice data, text data, and facial expression image data. From this data, the emotion engine identifies the user's current emotional state. Specifically, it uses voice analysis, text analysis, and image analysis algorithms to generate an emotional status, such as "I want to relax." The analysis results are output as emotional information.

[0485] Step 4:

[0486] The device sends prompt information and emotional information, which is the analysis result of the emotion engine, to the server. The data sent includes the user's cooking request (prompt information) and emotional data obtained through analysis, such as "I want to relax."

[0487] Step 5:

[0488] The server analyzes the prompt information and emotional information it receives. It uses natural language processing and facial expression analysis technologies to understand the user's input and emotions. Based on these results, it selects the optimal generation algorithm. For example, if the emotion is relaxed, it determines that a light dish would be appropriate. The input for the analysis is the prompt information and emotional data, and the output is the analysis result based on the selected algorithm.

[0489] Step 6:

[0490] The server uses a selected generation algorithm to recommend the best dish based on prompt and emotion information. During this generation process, dishes that match the criteria are extracted from a specific food database and selected as final candidates. The output includes dish candidates such as "cold soba noodles" and "refreshing salad."

[0491] Step 7:

[0492] The server sends the recommended dishes back to the user's device, which then displays the received dish information on the application's user interface. The user can then select from the dishes presented and confirm their order.

[0493] Step 8:

[0494] The user finally selects the food they want to order and confirms the order. By pressing the confirm button, the food ordering process is completed. The food selected by the user is sent as order data, and the food delivery service begins the process of delivering the food.

[0495] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0496] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0497] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0498] [Second embodiment]

[0499] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0500] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0501] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0502] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0503] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0504] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0505] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0506] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0507] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0508] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0509] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0510] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0511] The present invention relates to a system for automatically generating storyboards based on prompt information entered by a user. The following describes the program processing and specific examples of the system.

[0512] System configuration and operation

[0513] 1. User enters prompt

[0514] The user launches the application on their device (e.g., PC or smartphone) and logs in. They click the "Create a new project" button and fill out a form to enter prompt information (title, scene, action, location, etc.) based on their video idea.

[0515] 2. Sending prompt information

[0516] The terminal collects the prompt information input by the user, generates an API request to transmit the information to the server, and transmits the request to the server.

[0517] 3. Parsing prompt information

[0518] The server analyzes the received prompt information, understands the content using natural language processing technology, and then selects the optimal generation algorithm (e.g., GPT-3 or image generation technology) based on the prompt information.

[0519] 4. Storyboard generation

[0520] The server uses a selected generation algorithm to generate a storyboard based on the prompt information, which contains specific instructions for each scene and action in the video.

[0521] 5. Returning the storyboard

[0522] The server sends the generated storyboard back to the user's device as an API response, and the device analyzes the received data and displays it on the user interface.

[0523] 6. User Review and Editing

[0524] The user can check the storyboard displayed on the terminal and make edits as necessary. Once the storyboard has been edited, the user can confirm it by clicking the final confirmation button.

[0525] Specific examples

[0526] For example, let's say a user wants to create a short comedy video about a clumsy friend trying to give something they forgot in the school hallway. The user would enter the prompt information as follows:

[0527] Title: "Forgotten Things"

[0528] Scene: School hallway

[0529] Action: Handing something back to a friend, making a mistake

[0530] Location: School hallway

[0531] The device sends these prompts to the server, which analyzes the information and selects an appropriate generation algorithm. The generation algorithm generates a storyboard, and the output is a storyboard containing the following scenes:

[0532] 1. Scene 1: In the school hallway, a friend comes running with something they forgot.

[0533] 2. Scene 2: Your friend slips and falls.

[0534] 3. Scene 3: The friend laughs and hands over the forgotten item.

[0535] The storyboard is sent back to the device from the server, where the user can review and edit it. For example, the user can add details about "why the friend fell" in Scene 2. Finally, the storyboard is finalized to the user's satisfaction, and the video is shot based on it.

[0536] In this way, the system of the present invention allows users to easily create specific storyboards and efficiently proceed with professional video production.

[0537] The processing flow will be explained below.

[0538] Step 1: User enters prompt information

[0539] The user starts the application on the terminal and logs in.

[0540] The user clicks the "Create a new project" button, which displays a form for entering prompt information.

[0541] The user enters information such as title, scene, action, location, etc. into the input fields and clicks the "Submit" button.

[0542] Step 2: The device sends the prompt information to the server

[0543] The terminal collects the prompt information entered by the user.

[0544] The device generates an API request to send the collected prompt information to the server.

[0545] The device executes an API request and sends the prompt information to the server.

[0546] Step 3: The server parses the prompt information

[0547] The server uses natural language processing techniques to parse the received prompt information.

[0548] The server interprets the contents of the prompt information and selects a generation algorithm based on the analysis results.

[0549] Step 4: The server generates the storyboard using a generation algorithm

[0550] The server generates the storyboard using a selected generation algorithm (e.g., GPT-3 or image generation technology).

[0551] Based on the prompt information, the server creates a storyboard containing specific instructions for each scene and action.

[0552] Step 5: The server sends the generated storyboard back to the device

[0553] The server prepares an API response to send the generated storyboard to the user's device.

[0554] The server executes the API response and sends the storyboard to the device.

[0555] Step 6: The device displays the storyboard, and the user checks and edits it.

[0556] The terminal analyzes the received storyboard data and displays it on the user interface.

[0557] The user can check the displayed storyboard and edit each scene and action as necessary.

[0558] When the user has finished editing, he clicks the "Save" button.

[0559] Step 7: The device sends the edited storyboard to the server

[0560] The device generates an API request to send the storyboard that the user has edited and confirmed to the server.

[0561] The device executes an API request and sends the edited storyboard to the server.

[0562] Step 8: The server saves the final storyboard and notifies you that the confirmation is complete

[0563] The server stores the received final storyboard data in a database.

[0564] The server prepares an API response to notify the device that the final storyboard has been confirmed.

[0565] The server executes the API response and sends a confirmation completion notification to the terminal.

[0566] By following the steps above, users can efficiently generate concrete storyboards and use them as a guide for video production.

[0567] Example 1

[0568] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0569] In conventional video production, creating storyboards requires specialized knowledge and effort, making it difficult for beginners and general users. Furthermore, creating storyboards manually takes time and effort, hindering efficient video production. Therefore, there has been a demand for a system that allows users to easily and efficiently create and edit storyboards.

[0570] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0571] In this invention, the server includes means for transmitting prompt information from the user's terminal to the server, means for the server to analyze the prompt information using natural language processing technology, and means for the server to select an optimal generation algorithm using the natural language processing technology. This makes it possible to efficiently generate a specific storyboard based on the prompt information entered by the user and return the storyboard to the user.

[0572] "Prompt information" is information that a user inputs based on an idea for a video, and includes details such as title, scenes, actions, and locations.

[0573] The "means for analyzing" is a function for understanding and analyzing the content of the prompt information received by the server using natural language processing technology.

[0574] The "generation algorithm" is an algorithm used to generate a storyboard based on prompt information, and specifically includes natural language processing technology and image generation technology.

[0575] A "storyboard" is a visual sketch or depiction that contains specific instructions for each scene or action in a video.

[0576] The "means for returning" is a function for returning the storyboard generated by the server to the user's device, and is performed as an API response.

[0577] The "display and editing means" refers to an interface and functionality that allows the received storyboard to be displayed on the user terminal and for the user to edit it as needed.

[0578] "Natural language processing technology" is a technology that enables computers to understand and analyze human language, and is used to select generation algorithms and analyze prompt information.

[0579] "Image generation technology" refers to technology that allows a computer to generate images based on prompt information, creating a concrete visual depiction of the storyboard.

[0580] An "API request" is a communication request from a user terminal to a server to request the operation of a specific service, and is used when sending prompt information.

[0581] An "API response" is response data returned from the server to the user terminal, and includes the generated storyboard.

[0582] The present invention relates to a system for automatically generating storyboards based on prompt information entered by a user. The program processing of the system and an embodiment thereof will be specifically described below.

[0583] System configuration

[0584] The system uses user terminals, servers, and API requests and responses to communicate between them.

[0585] 1. User enters prompt

[0586] The user launches the application on their device (such as a PC or smartphone) and logs in. After logging in, the user clicks the "Create a new project" button and enters information into a form for entering prompt information (such as title, scene, action, location, etc.). This prompt information is used to generate a storyboard.

[0587] Software used: Web application, mobile application

[0588] 2. Sending prompt information

[0589] The terminal collects the prompt information entered by the user and generates an API request as JSON formatted data, which is then sent to the server using the HTTP POST method.

[0590] Technologies used: RESTful API, JSON data format

[0591] 3. Parsing prompt information

[0592] The server analyzes the received prompt information using natural language processing technology. Specifically, it uses a natural language processing engine (e.g., NLTK or Spacy) to analyze the prompt information and understand its content. Based on the analysis results, it selects the optimal generation algorithm (e.g., the generative AI model GPT-3 or image generation technology).

[0593] Software used: NLTK, Spacy, GPT-3

[0594] 4. Storyboard generation

[0595] The server uses the selected generation algorithm to generate a storyboard based on the prompt information. Specifically, it uses GPT-3 to generate detailed scene descriptions and image generation technology to create specific scene images. These are then combined to create the storyboard.

[0596] Technologies used: GPT-3, image generation technology

[0597] 5. Returning the storyboard

[0598] The server returns the generated storyboard to the user's device as an API response, which is also in JSON format.

[0599] Technologies used: RESTful API, JSON data format

[0600] 6. User Review and Editing

[0601] The user can check the storyboard displayed on the terminal and make edits as necessary. Once editing is complete, the user clicks the final confirmation button to finalize the storyboard.

[0602] Software used: Web application, mobile application

[0603] Specific examples

[0604] As an example, suppose a user wants to create a short comedy video about "making a mistake while trying to give something to a friend in the school hallway."

[0605] Example of user prompt input

[0606] Title: "Forgotten Things"

[0607] Scene: School hallway

[0608] Action: Handing something back to a friend, making a mistake

[0609] Location: School hallway

[0610] The user inputs this information into the application, and the device sends it to the server. The server analyzes the information and selects an appropriate generation algorithm. The generation algorithm generates a storyboard containing the following scenes:

[0611] 1. Scene 1: In the school hallway, a friend comes running with something they forgot.

[0612] 2. Scene 2: Your friend slips and falls.

[0613] 3. Scene 3: The friend laughs and hands over the forgotten item.

[0614] The server sends the storyboard back to the device, where the user can review and edit it. For example, the user can add details about "why the friend fell" in Scene 2.

[0615] In this way, the system of the present invention enables efficient video production by allowing users to easily create and edit specific storyboards.

[0616] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0617] Step 1: User Enters Prompt

[0618] The user launches the application on their device (PC, smartphone, etc.) and logs in. After logging in, they click the "Create a new project" button and enter the prompt information (title, scene, action, location, etc.) in the form.

[0619] Input: Prompt information entered by the user (title, scene, action, location)

[0620] Output: The prompt information entered is saved in the form

[0621] Specific behavior:

[0622] Start the application and enter your user ID and password in the login form.

[0623] After logging in, on the dashboard screen, click the "Create a new project" button.

[0624] In the form that appears, enter the title "Forgotten Item," the scene "School Hallway," the action "Giving forgotten item to friend, making a mistake," and the location "School Hallway."

[0625] Step 2: Send prompt information

[0626] The terminal collects the prompt information entered by the user and generates an API request, which is then sent to the server using the HTTP POST method.

[0627] Input: The prompt information entered by the user.

[0628] Output: The generated API request is sent to the server.

[0629] Specific behavior:

[0630] Collect prompt information as JSON format data and generate an API request.

[0631] Send an API request to the server using the HTTP POST method.

[0632] Wait for a response from the server.

[0633] Step 3: Parse prompt information

[0634] The server analyzes the received prompt information using natural language processing technology. Specifically, it uses a natural language processing engine (such as NLTK or Spacy) to analyze the prompt information and understand its content.

[0635] Input: Received prompt information

[0636] Output: Analysis results (understanding the contents of prompt information)

[0637] Specific behavior:

[0638] The server receives the API request.

[0639] The received prompt information is analyzed using a natural language processing engine.

[0640] As a result of the analysis, data that understands the content of the prompt information is generated.

[0641] Step 4: Selecting a generation algorithm

[0642] The server selects the optimal generation algorithm (e.g., GPT-3 or image generation technology) based on the analysis results.

[0643] Input: Analysis result of prompt information

[0644] Output: The selected generation algorithm

[0645] Specific behavior:

[0646] Based on the analysis results of the prompt information, candidate generation algorithms are evaluated.

[0647] The most suitable algorithm is selected from among those such as GPT-3 and image generation technology.

[0648] Record the selected generation algorithm.

[0649] Step 5: Generate the storyboard

[0650] The server uses the selected generation algorithm to generate a storyboard based on the prompt information. Specifically, it uses GPT-3 to generate detailed scene descriptions and image generation technology to create specific scene images. These are then combined to create the storyboard.

[0651] Input: Selected generation algorithm, prompt information

[0652] Output: Generated storyboard

[0653] Specific behavior:

[0654] Use GPT-3 to generate detailed scene descriptions based on prompt information.

[0655] Image generation techniques are used to create concrete scene images based on scene descriptions.

[0656] Integrate the scene description with the generated images to build a complete storyboard.

[0657] Step 6: Return the storyboard

[0658] The server returns the generated storyboard to the user's device as an API response, which is also in JSON format.

[0659] Input: Generated storyboard

[0660] Output: Storyboard data as API response

[0661] Specific behavior:

[0662] Convert the generated storyboard into JSON format.

[0663] As an API response, the storyboard is returned to the device in an HTTP response message.

[0664] Step 7: User review and editing

[0665] The user checks the storyboard displayed on the terminal and makes edits as necessary. Once editing is complete, the user clicks the final confirmation button to finalize the storyboard.

[0666] Input: Returned storyboard

[0667] Output: Finalized storyboard

[0668] Specific behavior:

[0669] Check the storyboard on the device's UI.

[0670] Add details or modify scenes and actions as needed.

[0671] Once you're done editing, click the "Final Confirm" button to finalize the storyboard.

[0672] (Application example 1)

[0673] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0674] Conventional storyboard generation systems can automatically generate storyboards based on prompt information entered by the user, but they have limited means for sharing the generated storyboards with other users. Furthermore, they lack an interface or means for users to easily edit the storyboards they generate and use them to create videos. Therefore, there is a need for a system that allows users to efficiently share generated storyboards and easily edit and use them.

[0675] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0676] In this invention, the server includes means for receiving a plurality of pieces of prompt information input by a user, means for analyzing the prompt information, means for selecting a generation algorithm based on the analysis result, means for generating a storyboard using the selected generation algorithm, means for returning the generated storyboard to the user, means for displaying and editing the returned storyboard, and means for sharing the generated storyboard with other users via a content sharing service. This enables users to efficiently share the generated storyboard with other users and use it for editing or video production.

[0677] "Prompt information" refers to information that a user inputs to generate a storyboard, specifically, titles, scenes, actions, and locations.

[0678] A "generation algorithm" is an algorithm that analyzes input prompt information and generates content such as storyboards based on that information, and primarily includes natural language processing technology and image generation technology.

[0679] A "storyboard" is a visual illustration that shows the elements and movements of each scene in order to plan and execute video production.

[0680] The "content sharing service" refers to a service via the Internet for sharing content such as created storyboards with other users.

[0681] "Parsing" refers to the process of understanding the input prompt information and selecting an appropriate generation algorithm.

[0682] "User" refers to a person or organization that uses the storyboard generation system.

[0683] This invention relates to a system that automatically generates storyboards based on prompt information entered by users, and allows them to be shared and edited. The system's program uses the Python language, Flask (a web framework), and the OpenAI API. The user's smartphone functions as the terminal, and the server is the backend that processes requests from users.

[0684] System configuration and operation

[0685] 1. User enters prompt

[0686] The user launches the smartphone application and logs in. The user presses a button to create a new project and fills in a form to enter prompt information based on the video idea. The prompt information includes the title, scene, action, and location. This information is sent from the user's device to the server.

[0687] 2. Parsing prompt information

[0688] The server receives the prompt information entered by the user and analyzes the content using natural language processing technology. Specifically, it uses a generative AI model such as OpenAI's GPT-3 to understand the meaning of the prompt information and select an appropriate generation algorithm.

[0689] 3. Storyboard generation

[0690] The server uses the selected generation algorithm to generate a storyboard based on the prompt information, which contains specific instructions for each scene and action in the video.

[0691] 4. Return and display of storyboards

[0692] The server returns the generated storyboard to the user's device, which receives the data returned as an API response and displays it on the user interface.

[0693] 5. User Editing and Sharing

[0694] The user can check the storyboard displayed on the device and edit it as necessary. Once edited, the storyboard can be shared with other users via a content sharing service.

[0695] Hardware and software used

[0696] Hardware: Smartphone (terminal) and server

[0697] Software: Python (programming language), Flask (web framework), OpenAI API (generative AI model)

[0698] Specific examples

[0699] For example, if a user enters the video idea "Morning yoga by a tranquil lake with a sunrise in the background" as a prompt, they would enter the following information:

[0700] Title: "Morning Yoga"

[0701] Scene: A calm lake with a sunrise in the background

[0702] Movement: Yoga pose

[0703] This prompt information is sent to the server in the following format:

[0704] Generate a storyboard: Title: "Morning Yoga", Scene: Calm lake with sunrise in the background, Action: Striking a yoga pose

[0705] The server parses this information and generates a storyboard like this:

[0706] 1. Scene 1: The sun begins to rise, revealing a tranquil scene over a lake.

[0707] 2. Scene 2: The protagonist lays out her yoga mat and begins getting ready.

[0708] 3. Scene 3: She is shown performing a yoga pose.

[0709] The generated storyboard is returned to the user and displayed on their device, where the user can edit it as needed and ultimately share it with other users via a content sharing service.

[0710] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0711] Step 1:

[0712] The user launches the smartphone application and logs in. They press the "Create a new project" button and fill out a form to enter prompt information based on their video idea. This information includes the title, scene, action, and location. The entered prompt information is temporarily saved on the device.

[0713] input:

[0714] Prompt information for user input (title, scene, action, location)

[0715] output:

[0716] Prompt information stored on the device

[0717] Step 2:

[0718] The device generates an API request to send the saved prompt information to the server and sends it to the server.

[0719] input:

[0720] Prompt information stored on the device

[0721] output:

[0722] API requests sent to the server

[0723] Step 3:

[0724] The server receives the API request and analyzes the sent prompt information. Using natural language processing technology, such as OpenAI's API, the server understands the content of the prompt information and selects the appropriate generation algorithm.

[0725] input:

[0726] API requests sent to the server

[0727] output:

[0728] Prompt information analysis results

[0729] Selected generation algorithm

[0730] Step 4:

[0731] The server uses a selected generation algorithm to generate a storyboard based on the prompt information, which contains specific instructions for each scene and action in the video.

[0732] input:

[0733] Prompt information analysis results

[0734] Selected generation algorithm

[0735] output:

[0736] Generated storyboard

[0737] Step 5:

[0738] The server sends the generated storyboard back to the user's device as an API response, and the device analyzes the received data and displays it on the user interface.

[0739] input:

[0740] Generated storyboard

[0741] output:

[0742] API response sent back to the device

[0743] Storyboard display on device

[0744] Step 6:

[0745] The user can check the storyboard displayed on the device and make edits as necessary. Once editing is complete, the storyboard is confirmed by pressing the final confirmation button.

[0746] input:

[0747] Storyboard displayed on the device

[0748] output:

[0749] User edited storyboard

[0750] Step 7:

[0751] The finalized storyboard can be shared with other users via a content sharing service. The server receives the share request and provides a share link to other users.

[0752] input:

[0753] Storyboard confirmed by user

[0754] output:

[0755] Storyboards shared through content sharing services

[0756] Shared link provided to other users

[0757] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0758] The present invention relates to a system that combines prompt information input by a user with an emotion engine that recognizes the user's emotions. Below, the processing of the system program and specific examples will be described.

[0759] System configuration and operation

[0760] 1. User enters prompt

[0761] The user launches the application on their device (e.g., PC or smartphone) and logs in. They click the "Create a new project" button and fill out a form to enter prompt information (title, scene, action, location, etc.) based on their video idea.

[0762] 2. Emotion recognition by emotion engine

[0763] The terminal operates an emotion engine that recognizes emotions from the user's facial expressions, voice, and input text while the user is entering prompt information. The emotion engine analyzes the user's current emotional state and transmits the results to the server.

[0764] 3. Sending prompt and emotional information

[0765] The terminal collects prompt information input by the user, generates an API request to be sent to the server together with emotion information obtained from the emotion engine, and sends the request to the server.

[0766] 4. Analysis of prompt information and emotional information

[0767] The server analyzes the received prompt and emotional information, understands the content using natural language processing and facial expression analysis technologies, and then selects the optimal generation algorithm (e.g., GPT-3 or image generation technology) based on the prompt and emotional information.

[0768] 5. Storyboard Generation

[0769] The server uses the selected generation algorithm to generate a storyboard based on the prompt information and the emotion information, which includes specific instructions for each scene and action in the video and elements that reflect the user's emotional state.

[0770] 6. Returning the storyboard

[0771] The server sends the generated storyboard back to the user's device as an API response, and the device analyzes the received data and displays it on the user interface.

[0772] 7. User Review and Editing

[0773] The user can check the storyboard displayed on the terminal and make edits as necessary. Once the storyboard has been edited, the user can confirm it by clicking the final confirmation button.

[0774] Specific examples

[0775] For example, let's say a user wants to create a short comedy video about a clumsy friend trying to give something they forgot in the school hallway. The user would enter the prompt information as follows:

[0776] Title: "Forgotten Things"

[0777] Scene: School hallway

[0778] Action: Handing something back to a friend, making a mistake

[0779] Location: School hallway

[0780] At the same time, the emotion engine analyzes the user's facial expressions and voice while inputting and recognizes that the user is in a happy emotional state. The device then transmits this prompt information and emotion information to the server.

[0781] The server analyzes the information and selects the appropriate generation algorithm, which generates the storyboard and outputs a storyboard containing the following scenes:

[0782] 1. Scene 1: In the school hallway, a friend comes running with something they forgot. They look happy.

[0783] 2. Scene 2: A friend slips and falls. Happy expressions and actions.

[0784] 3. Scene 3: The friend laughs and hands over the forgotten item.

[0785] The server sends the storyboard back to the device, where the user can review and edit it. For example, the user can add details about "why the friend fell" in Scene 2. Finally, once the user is satisfied with the storyboard, the video is shot.

[0786] In this way, the system of the present invention allows the user to easily create specific storyboards and efficiently proceed with the production of professional videos that reflect the user's emotions.

[0787] The processing flow will be explained below.

[0788] Step 1: User enters prompt information

[0789] The user starts the application on the terminal and logs in.

[0790] The user clicks the "Create a new project" button, which displays a form for entering prompt information.

[0791] The user enters information such as title, scene, action, location, etc. into the input fields and clicks the "Submit" button.

[0792] Step 2: The device activates the emotion engine

[0793] The terminal runs the emotion engine while the user is entering the prompt information.

[0794] The emotion engine uses a camera and microphone to analyze the user's facial expressions and voice in real time.

[0795] Step 3: The device sends prompt information and emotion information to the server.

[0796] The terminal collects the prompt information input by the user and combines it with the emotion information obtained from the emotion engine into one data packet.

[0797] The device generates an API request for transmitting the collected prompt information and emotion information to the server, and sends the request to the server.

[0798] Step 4: The server analyzes the prompt and emotion information

[0799] The server analyzes the received prompt information and emotion information.

[0800] The server uses natural language processing technology to analyze the content of the prompt information and uses the emotional information to understand the user's emotional state.

[0801] Based on the analysis results, the server selects the optimal generation algorithm based on prompt information and emotion information.

[0802] Step 5: The server generates the storyboard using a generation algorithm

[0803] The server uses a selected generation algorithm (e.g., GPT-3 or image generation technology) to generate a storyboard based on prompt information and emotion information.

[0804] The server creates a storyboard containing specific instructions for each scene and action, as well as elements that reflect the user's emotional state.

[0805] Step 6: The server sends the generated storyboard back to the device

[0806] The server prepares an API response to return the generated storyboard to the user's device.

[0807] The server executes the API response and sends the storyboard to the device.

[0808] Step 7: The device displays the storyboard, and the user checks and edits it.

[0809] The terminal analyzes the received storyboard data and displays it on the user interface.

[0810] The user checks the displayed storyboard and confirms the content of each scene and action.

[0811] The user edits the storyboard as needed and clicks the "Save" button.

[0812] Step 8: The device sends the edited storyboard to the server

[0813] The device generates an API request to send the storyboard that the user has edited and confirmed to the server.

[0814] The device executes an API request and sends the edited storyboard to the server.

[0815] Step 9: The server saves the final storyboard and notifies you that the confirmation is complete

[0816] The server stores the received final storyboard data in a database.

[0817] The server prepares an API response to notify the device that the final storyboard has been confirmed.

[0818] The server executes the API response and sends a confirmation completion notification to the terminal.

[0819] Through the above steps, users can efficiently create detailed storyboards and proceed with the production of professional videos that reflect emotions.

[0820] Example 2

[0821] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0822] Conventional storyboard generation systems have difficulty reflecting user emotions, and because they generate content based solely on prompt information, they lack the subtle nuances and emotional expression desired by users. Furthermore, users sometimes find it difficult to clearly communicate their emotions, which can result in generated content that deviates from the user's intentions. Therefore, there has been a demand for a system that generates storyboards that effectively reflect user emotions.

[0823] The specification processing by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving a plurality of pieces of prompt information input by the user, means for analyzing the prompt information, means for selecting a generation algorithm based on the analysis result, means for generating a storyboard using the selected generation algorithm, means for returning the generated storyboard to the user, means for displaying and editing the returned storyboard, means for detecting the user's emotions and analyzing the emotion information together with the prompt information, and means for including emotion-reflecting elements in a storyboard generated based on the analyzed emotion information. This makes it possible to generate a storyboard that reflects the user's emotions.

[0824] "Prompt information" is information based on the idea of ​​the video, such as title, scene, action, location, etc., entered by the user.

[0825] An "emotion engine" is software that detects emotions by analyzing a user's facial expressions, voice, input text, etc.

[0826] A "generation algorithm" is an algorithm used to generate a storyboard or the like based on prompt information and emotion information.

[0827] A "storyboard" is a visual storyboard that contains specific instructions for each scene and action in a video, as well as elements that reflect the user's emotional state.

[0828] The "server" is a computer system that analyzes prompt information and emotional information, selects a generation algorithm based on that information, generates a storyboard, and returns it to the terminal.

[0829] A "terminal" is a device, such as a personal computer or smartphone, through which a user inputs prompt information and checks and edits the generated storyboard.

[0830] "Analysis means" refers to a method or function for understanding received prompt information and emotion information and performing processing based on that information.

[0831] "Emotion-reflecting elements" are elements that are reflected in the storyboard based on the user's emotional information, and include, for example, the facial expressions and movements of characters.

[0832] "Natural language processing" is the technology that enables computers to understand and generate human language.

[0833] "Image generation technology" is a technology that allows computers to generate visual content.

[0834] The present invention relates to a system that combines prompt information input by a user with an emotion engine that recognizes the user's emotions. Below, the processing of the system program and specific examples will be described.

[0835] System configuration and operation

[0836] This system consists of three main components: the user, the device, and the server. The user inputs prompt information using the device, and the device analyzes the user's emotions using an emotion engine. The analyzed prompt information and emotion information are sent to the server, which then generates a storyboard based on this and sends it back to the device.

[0837] 1. User enters prompt

[0838] A user launches the application on a device (such as a PC or smartphone) and logs in. The user clicks the "Create a new project" button and enters prompt information based on their video idea, including title, scene, action, location, etc.

[0839] 2. Emotion recognition by emotion engine

[0840] The device activates an emotion engine to analyze the user's facial expressions, voice, and input text to determine their emotions. This emotion information reflects the user's current emotional state and is temporarily stored on the device along with the prompt information.

[0841] 3. Sending prompt and emotional information

[0842] The device sends the prompt information entered by the user and the emotion information analyzed by the emotion engine to the server via an API request.

[0843] 4. Analysis of prompt information and emotional information

[0844] The server analyzes the received prompt information and emotional information. Specifically, it uses natural language processing technology (e.g., GPT-3) and facial expression analysis technology to understand the content and emotion of the prompt. Based on the analysis results, it selects the optimal generation algorithm.

[0845] 5. Storyboard Generation

[0846] The server uses the selected generation algorithm to generate a storyboard based on the prompt information and the emotion information, which includes specific instructions for each scene and elements that reflect the user's emotional state.

[0847] 6. Returning the storyboard

[0848] The server returns the generated storyboard to the device as an API response, and the device displays the received storyboard on the user interface for the user to confirm.

[0849] 7. User Review and Editing

[0850] The user checks the displayed storyboard and makes edits as necessary. Once editing is complete, the user clicks the "Final Confirm" button to finalize the storyboard.

[0851] Specific examples

[0852] For example, let's say a user wants to create a short comedy video about a clumsy friend trying to give something they forgot in the school hallway. The user would enter the prompt information as follows:

[0853] Title: "Forgotten Things"

[0854] Scene: School hallway

[0855] Action: Handing something back to a friend, making a mistake

[0856] Location: School hallway

[0857] At the same time, the emotion engine analyzes the user's facial expressions and voice while inputting and recognizes that the user is in a happy emotional state. The device then transmits this prompt information and emotion information to the server.

[0858] The server analyzes the information and selects the appropriate generation algorithm, which generates a storyboard containing the following scenes:

[0859] 1. Scene 1: In the school hallway, a friend comes running with something they forgot. They look happy.

[0860] 2. Scene 2: A friend slips and falls. Happy expressions and actions.

[0861] 3. Scene 3: The friend laughs and hands over the forgotten item.

[0862] The server sends the storyboard back to the device, where the user can review and edit it. For example, the user can add details about "why the friend fell" in Scene 2. Finally, once the user is satisfied with the storyboard, the video is shot.

[0863] In this way, the system allows users to easily create specific storyboards and efficiently create professional videos that reflect the user's emotions.

[0864] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0865] Step 1:

[0866] The user launches the application on the terminal and logs in.

[0867] Input: User login information (username, password).

[0868] How it works: A user goes to a terminal, opens an application, and enters their username and password into the login form.

[0869] Output: The application dashboard screen is displayed.

[0870] Step 2:

[0871] User clicks the "Create a new project" button and fills in prompt information based on their video idea.

[0872] Input: Prompt information (title, scene, action, location).

[0873] Action: The user writes down their video idea in a form where they enter prompt information. For example, "Title: Lost Item, Scene: School Hallway, Action: Handing Over Lost Item to Friend, Making a Mistake, Location: School Hallway."

[0874] Output: The entered prompt information is temporarily saved on the terminal.

[0875] Step 3:

[0876] The device activates an emotion engine and analyzes emotions from the user's facial expressions, voice, and input text.

[0877] Input: User's facial expression data, voice data, input text.

[0878] How it works: The device uses a camera and microphone to record the user's facial expressions and voice, which are then analyzed by the emotion engine. For example, if the user is laughing happily, the emotion engine will detect "happiness."

[0879] Output: Generate emotional information (e.g., enjoyment) and temporarily store it on the device.

[0880] Step 4:

[0881] The terminal transmits prompt information and emotion information to the server.

[0882] Input: prompt information, emotion information.

[0883] How it works: The device collects this information, converts it into JSON format, and sends it to the server as an API request.

[0884] Output: The server receives the prompt information and emotion information.

[0885] Step 5:

[0886] The server analyzes the received prompt information and emotion information.

[0887] Input: Received prompt information, emotion information.

[0888] How it works: The server uses natural language processing technology (such as GPT-3) and facial expression analysis technology to analyze the content and sentiment of the prompt.

[0889] Output: Based on the analysis results, the optimal generative algorithm is selected (e.g., GPT-3 model).

[0890] Step 6:

[0891] The server uses a selected generation algorithm to generate a storyboard based on the prompt information and the emotion information.

[0892] Input: Parsed prompt information, sentiment information, selected generation algorithm.

[0893] How it works: The server uses GPT-3 to automatically generate a storyboard, for example, a storyboard containing scenes such as "Scene 1: School hallway, a friend comes running with something they forgot. Happy expression."

[0894] Output: Storyboard data is generated.

[0895] Step 7:

[0896] The server returns the generated storyboard to the terminal.

[0897] Input: The generated storyboard data.

[0898] Operation: The server sends the storyboard data to the device as an API response.

[0899] Output: The device receives the storyboard data.

[0900] Step 8:

[0901] The terminal displays the received storyboard on the user interface and allows the user to check it.

[0902] Input: Received storyboard data.

[0903] Action: The device parses the received data and displays it in its interface for the user to review.

[0904] Output: The generated storyboard is displayed to the user.

[0905] Step 9:

[0906] The user checks the displayed storyboard and makes edits as necessary.

[0907] Input: The displayed storyboard.

[0908] Action: The user edits the storyboard using a tablet pen or mouse. For example, adding "Why did my friend fall down?" in Scene 2. Once editing is complete, the user clicks the "Final Confirm" button to finalize the storyboard.

[0909] Output: Edited and finalized storyboard.

[0910] (Application example 2)

[0911] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0912] In modern society, users' meal choices vary greatly depending on their mood and emotions on that day. However, conventional food delivery services lack the ability to recommend dishes that take the user's emotional state into account. As a result, it is difficult for users to achieve sufficient satisfaction when choosing a meal. In particular, there is a need for food recommendations that accurately reflect the user's emotions.

[0913] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0914] In this invention, the server includes means for receiving a plurality of pieces of prompt information input by the user, means for analyzing the prompt information and emotion data, means for selecting a generation algorithm based on the analysis results, means for analyzing the emotion information obtained from the emotion engine, means for recommending an optimal dish based on the prompt information and emotion information, and means for returning the recommended dish to the user, thereby enabling recipe suggestions that comprehensively consider the user's emotional state.

[0915] "User-entered prompt information" refers to a number of pieces of information entered by a user to embody a specific request or idea, including title, scene, action, location, food request, etc.

[0916] "Means for analyzing prompt information" refers to a processing function for analyzing the input prompt information in detail and understanding the user's intentions and goals.

[0917] The "means for selecting a generation algorithm" is a processing mechanism for determining an optimal generation algorithm based on the analyzed prompt information and emotion data.

[0918] The "means for generating a storyboard using a selected generation algorithm" is a function that uses a selected generation algorithm to automatically generate a storyboard that serves as a blueprint for a video or image.

[0919] The "means for returning the generated storyboard to the user" refers to a means for transmitting the generated storyboard to the user's terminal so that it can be displayed and edited.

[0920] "Means for displaying and editing the returned storyboard" refers to a function that allows the user to display the received storyboard on the terminal and edit or modify it as necessary.

[0921] The "emotion engine" is an analysis engine that analyzes the user's voice data, text data, and facial expression image data to identify the user's current emotional state.

[0922] "Means for integrating emotional information into analysis results" refers to a function that combines emotional information obtained from the emotion engine with the analysis results of prompt information to achieve comprehensive understanding.

[0923] The "means for recommending the most suitable dish" is a function for suggesting a dish that matches the user's emotional state and request based on the analyzed prompt information and emotional information.

[0924] The "means for returning recommended dishes to the user" refers to a means for sending information about the selected dishes to the user's terminal and suggesting them to the user.

[0925] The present invention relates to a food delivery application that recommends dishes taking into account the emotional state of the user. Specific embodiments for implementing the present invention will be described below.

[0926] System configuration

[0927] This system consists of an application that runs on the user's device, such as a smartphone or PC, and an emotion engine and generation algorithm that runs on the server side.

[0928] procedure

[0929] 1. User enters prompt

[0930] The user launches the application and enters their meal preference as a prompt, for example, a request such as "I would like something light."

[0931] 2. Emotion recognition by emotion engine

[0932] The device collects the user's voice data, text data, and facial expression image data when prompting, and sends them to the emotion engine, which analyzes this data and identifies the user's current emotional state.

[0933] 3. Sending prompt and emotional information

[0934] The device sends the prompt information and analyzed emotion data to the server, which then selects a generation algorithm based on this information.

[0935] 4. Food Recommendations

[0936] The server-side algorithm analyzes prompt and emotion information to recommend the most suitable dish. For example, if a user feels tired and wants to refresh, it will recommend cold soba noodles or a refreshing salad.

[0937] 5. Returning Recommendations

[0938] The server returns recommended dish information to the user's terminal, and the user can order dishes based on this information.

[0939] Hardware and software used

[0940] Hardware: Smartphones, PCs

[0941] Software: Sentiment analysis API (Python library), food delivery API

[0942] Data format: JSON format, text data, audio data, image data

[0943] Specific examples

[0944] For example, consider a case where a user feels tired and wants to relax. The user inputs into the app, "I'm tired, I want to relax. I want to eat something refreshing." The emotion engine analyzes the user's voice and facial expressions to determine that the user wants to relax. Based on the results of the analysis on the server side, recommendations such as "cold soba noodles" or "refreshing salad" are sent back to the user.

[0945] This allows users to easily order the food that best suits their emotional state at the time.

[0946] Examples of prompt statements include "I would like to eat something light," "I would like some spicy Chinese food," and "I would like to eat a special dessert."

[0947] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0948] Step 1:

[0949] A user launches the application and inputs a desired dish as a prompt. For example, the user may input "I want something light." The prompt information input by the user is collected in an input field of the application. The input data includes the user's request.

[0950] Step 2:

[0951] The device collects the user's voice data, text data, and facial expression image data. It prepares to send this data to the emotion engine. The collected data includes voice files (e.g., "I'm tired, I want to calm down"), text data, and image files (user's facial expressions).

[0952] Step 3:

[0953] The emotion engine analyzes the collected voice data, text data, and facial expression image data. From this data, the emotion engine identifies the user's current emotional state. Specifically, it uses voice analysis, text analysis, and image analysis algorithms to generate an emotional status, such as "I want to relax." The analysis results are output as emotional information.

[0954] Step 4:

[0955] The device sends prompt information and emotional information, which is the analysis result of the emotion engine, to the server. The sent data includes the user's cooking request (prompt information) and emotional data obtained through analysis, such as "I want to relax."

[0956] Step 5:

[0957] The server analyzes the prompt information and emotional information it receives. It uses natural language processing and facial expression analysis technologies to understand the user's input and emotions. Based on these results, it selects the optimal generation algorithm. For example, if the emotion is relaxed, it determines that a light dish would be appropriate. The input for the analysis is the prompt information and emotional data, and the output is the analysis result based on the selected algorithm.

[0958] Step 6:

[0959] The server uses a selected generation algorithm to recommend the best dish based on prompt and emotion information. During this generation process, dishes that match the criteria are extracted from a specific food database and selected as final candidates. The output includes dish candidates such as "cold soba noodles" and "refreshing salad."

[0960] Step 7:

[0961] The server sends the recommended dishes back to the user's device, which then displays the received dish information on the application's user interface. The user can then select from the dishes presented and confirm their order.

[0962] Step 8:

[0963] The user finally selects the food they want to order and confirms the order. By pressing the confirm button, the food ordering process is completed. The food selected by the user is sent as order data, and the food delivery service begins the process of delivering the food.

[0964] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0965] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0966] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0967] [Third embodiment]

[0968] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0969] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0970] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0971] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0972] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0973] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0974] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0975] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0976] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0977] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0978] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0979] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0980] The present invention relates to a system for automatically generating storyboards based on prompt information entered by a user. The following describes the program processing and specific examples of the system.

[0981] System configuration and operation

[0982] 1. User enters prompt

[0983] The user launches the application on their device (e.g., PC or smartphone) and logs in. They click the "Create a new project" button and fill out a form to enter prompt information (title, scene, action, location, etc.) based on their video idea.

[0984] 2. Sending prompt information

[0985] The terminal collects the prompt information input by the user, generates an API request to transmit the information to the server, and transmits the request to the server.

[0986] 3. Parsing prompt information

[0987] The server analyzes the received prompt information, understands the content using natural language processing technology, and then selects the optimal generation algorithm (e.g., GPT-3 or image generation technology) based on the prompt information.

[0988] 4. Storyboard generation

[0989] The server uses a selected generation algorithm to generate a storyboard based on the prompt information, which contains specific instructions for each scene and action in the video.

[0990] 5. Returning the storyboard

[0991] The server sends the generated storyboard back to the user's device as an API response, and the device analyzes the received data and displays it on the user interface.

[0992] 6. User Review and Editing

[0993] The user can check the storyboard displayed on the terminal and make edits as necessary. Once the storyboard has been edited, the user can confirm it by clicking the final confirmation button.

[0994] Specific examples

[0995] For example, let's say a user wants to create a short comedy video about a clumsy friend trying to give something they forgot in the school hallway. The user would enter the prompt information as follows:

[0996] Title: "Forgotten Things"

[0997] Scene: School hallway

[0998] Action: Handing something back to a friend, making a mistake

[0999] Location: School hallway

[1000] The device sends these prompts to the server, which analyzes the information and selects an appropriate generation algorithm. The generation algorithm generates a storyboard, and the output is a storyboard containing the following scenes:

[1001] 1. Scene 1: In the school hallway, a friend comes running with something they forgot.

[1002] 2. Scene 2: Your friend slips and falls.

[1003] 3. Scene 3: The friend laughs and hands over the forgotten item.

[1004] The storyboard is sent back to the device from the server, where the user can review and edit it. For example, the user can add details about "why the friend fell" in Scene 2. Finally, the storyboard is finalized to the user's satisfaction, and the video is shot based on it.

[1005] In this way, the system of the present invention allows users to easily create specific storyboards and efficiently proceed with professional video production.

[1006] The processing flow will be explained below.

[1007] Step 1: User enters prompt information

[1008] The user starts the application on the terminal and logs in.

[1009] The user clicks the "Create a new project" button, which displays a form for entering prompt information.

[1010] The user enters information such as title, scene, action, location, etc. into the input fields and clicks the "Submit" button.

[1011] Step 2: The device sends the prompt information to the server

[1012] The terminal collects the prompt information entered by the user.

[1013] The device generates an API request to send the collected prompt information to the server.

[1014] The device executes an API request and sends the prompt information to the server.

[1015] Step 3: The server parses the prompt information

[1016] The server uses natural language processing techniques to parse the received prompt information.

[1017] The server interprets the contents of the prompt information and selects a generation algorithm based on the analysis results.

[1018] Step 4: The server generates the storyboard using a generation algorithm

[1019] The server generates the storyboard using a selected generation algorithm (e.g., GPT-3 or image generation technology).

[1020] Based on the prompt information, the server creates a storyboard containing specific instructions for each scene and action.

[1021] Step 5: The server sends the generated storyboard back to the device

[1022] The server prepares an API response to send the generated storyboard to the user's device.

[1023] The server executes the API response and sends the storyboard to the device.

[1024] Step 6: The device displays the storyboard, and the user checks and edits it.

[1025] The terminal analyzes the received storyboard data and displays it on the user interface.

[1026] The user can check the displayed storyboard and edit each scene and action as necessary.

[1027] When the user has finished editing, he clicks the "Save" button.

[1028] Step 7: The device sends the edited storyboard to the server

[1029] The device generates an API request to send the storyboard that the user has edited and confirmed to the server.

[1030] The device executes an API request and sends the edited storyboard to the server.

[1031] Step 8: The server saves the final storyboard and notifies you that the confirmation is complete

[1032] The server stores the received final storyboard data in a database.

[1033] The server prepares an API response to notify the device that the final storyboard has been confirmed.

[1034] The server executes the API response and sends a confirmation completion notification to the terminal.

[1035] By following the steps above, users can efficiently generate concrete storyboards and use them as a guide for video production.

[1036] Example 1

[1037] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1038] In conventional video production, creating storyboards requires specialized knowledge and effort, making it difficult for beginners and general users. Furthermore, creating storyboards manually takes time and effort, hindering efficient video production. Therefore, there has been a demand for a system that allows users to easily and efficiently create and edit storyboards.

[1039] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1040] In this invention, the server includes means for transmitting prompt information from the user's terminal to the server, means for the server to analyze the prompt information using natural language processing technology, and means for the server to select an optimal generation algorithm using the natural language processing technology. This makes it possible to efficiently generate a specific storyboard based on the prompt information entered by the user and return the storyboard to the user.

[1041] "Prompt information" is information that a user inputs based on an idea for a video, and includes details such as title, scenes, actions, and locations.

[1042] The "means for analyzing" is a function for understanding and analyzing the content of the prompt information received by the server using natural language processing technology.

[1043] The "generation algorithm" is an algorithm used to generate a storyboard based on prompt information, and specifically includes natural language processing technology and image generation technology.

[1044] A "storyboard" is a visual sketch or depiction that contains specific instructions for each scene or action in a video.

[1045] The "means for returning" is a function for returning the storyboard generated by the server to the user's device, and is performed as an API response.

[1046] The "display and editing means" refers to an interface and functionality that allows the received storyboard to be displayed on the user terminal and for the user to edit it as needed.

[1047] "Natural language processing technology" is a technology that enables computers to understand and analyze human language, and is used to select generation algorithms and analyze prompt information.

[1048] "Image generation technology" refers to technology that allows a computer to generate images based on prompt information, creating a concrete visual depiction of the storyboard.

[1049] An "API request" is a communication request from a user terminal to a server to request the operation of a specific service, and is used when sending prompt information.

[1050] An "API response" is response data returned from the server to the user terminal, and includes the generated storyboard.

[1051] The present invention relates to a system for automatically generating storyboards based on prompt information entered by a user. The program processing of the system and an embodiment thereof will be specifically described below.

[1052] System configuration

[1053] The system uses user terminals, servers, and API requests and responses to communicate between them.

[1054] 1. User enters prompt

[1055] The user launches the application on their device (such as a PC or smartphone) and logs in. After logging in, the user clicks the "Create a new project" button and enters information into a form for entering prompt information (such as title, scene, action, location, etc.). This prompt information is used to generate a storyboard.

[1056] Software used: Web application, mobile application

[1057] 2. Sending prompt information

[1058] The terminal collects the prompt information entered by the user and generates an API request as JSON formatted data, which is then sent to the server using the HTTP POST method.

[1059] Technologies used: RESTful API, JSON data format

[1060] 3. Parsing prompt information

[1061] The server analyzes the received prompt information using natural language processing technology. Specifically, it uses a natural language processing engine (e.g., NLTK or Spacy) to analyze the prompt information and understand its content. Based on the analysis results, it selects the optimal generation algorithm (e.g., the generative AI model GPT-3 or image generation technology).

[1062] Software used: NLTK, Spacy, GPT-3

[1063] 4. Storyboard generation

[1064] The server uses the selected generation algorithm to generate a storyboard based on the prompt information. Specifically, it uses GPT-3 to generate detailed scene descriptions and image generation technology to create specific scene images. These are then combined to create the storyboard.

[1065] Technologies used: GPT-3, image generation technology

[1066] 5. Returning the storyboard

[1067] The server returns the generated storyboard to the user's device as an API response, which is also in JSON format.

[1068] Technologies used: RESTful API, JSON data format

[1069] 6. User Review and Editing

[1070] The user can check the storyboard displayed on the terminal and make edits as necessary. Once editing is complete, the user clicks the final confirmation button to finalize the storyboard.

[1071] Software used: Web application, mobile application

[1072] Specific examples

[1073] As an example, suppose a user wants to create a short comedy video about "making a mistake while trying to give something to a friend in the school hallway."

[1074] Example of user prompt input

[1075] Title: "Forgotten Things"

[1076] Scene: School hallway

[1077] Action: Handing something back to a friend, making a mistake

[1078] Location: School hallway

[1079] The user inputs this information into the application, and the device sends it to the server. The server analyzes the information and selects an appropriate generation algorithm. The generation algorithm generates a storyboard containing the following scenes:

[1080] 1. Scene 1: In the school hallway, a friend comes running with something they forgot.

[1081] 2. Scene 2: Your friend slips and falls.

[1082] 3. Scene 3: The friend laughs and hands over the forgotten item.

[1083] The server sends the storyboard back to the device, where the user can review and edit it. For example, the user can add details about "why the friend fell" in Scene 2.

[1084] In this way, the system of the present invention enables efficient video production by allowing users to easily create and edit specific storyboards.

[1085] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1086] Step 1: User Enters Prompt

[1087] The user launches the application on their device (PC, smartphone, etc.) and logs in. After logging in, they click the "Create a new project" button and enter the prompt information (title, scene, action, location, etc.) in the form.

[1088] Input: Prompt information entered by the user (title, scene, action, location)

[1089] Output: The prompt information entered is saved in the form

[1090] Specific behavior:

[1091] Start the application and enter your user ID and password in the login form.

[1092] After logging in, on the dashboard screen, click the "Create a new project" button.

[1093] In the form that appears, enter the title "Forgotten Item," the scene "School Hallway," the action "Giving forgotten item to friend, making a mistake," and the location "School Hallway."

[1094] Step 2: Send prompt information

[1095] The terminal collects the prompt information entered by the user and generates an API request, which is then sent to the server using the HTTP POST method.

[1096] Input: The prompt information entered by the user.

[1097] Output: The generated API request is sent to the server.

[1098] Specific behavior:

[1099] Collect prompt information as JSON format data and generate an API request.

[1100] Send an API request to the server using the HTTP POST method.

[1101] Wait for a response from the server.

[1102] Step 3: Parse prompt information

[1103] The server analyzes the received prompt information using natural language processing technology. Specifically, it uses a natural language processing engine (such as NLTK or Spacy) to analyze the prompt information and understand its content.

[1104] Input: Received prompt information

[1105] Output: Analysis results (understanding the contents of prompt information)

[1106] Specific behavior:

[1107] The server receives the API request.

[1108] The received prompt information is analyzed using a natural language processing engine.

[1109] As a result of the analysis, data that understands the content of the prompt information is generated.

[1110] Step 4: Selecting a generation algorithm

[1111] The server selects the optimal generation algorithm (e.g., GPT-3 or image generation technology) based on the analysis results.

[1112] Input: Analysis result of prompt information

[1113] Output: The selected generation algorithm

[1114] Specific behavior:

[1115] Based on the analysis results of the prompt information, candidate generation algorithms are evaluated.

[1116] The most suitable algorithm is selected from among those such as GPT-3 and image generation technology.

[1117] Record the selected generation algorithm.

[1118] Step 5: Generate the storyboard

[1119] The server uses the selected generation algorithm to generate a storyboard based on the prompt information. Specifically, it uses GPT-3 to generate detailed scene descriptions and image generation technology to create specific scene images. These are then combined to create the storyboard.

[1120] Input: Selected generation algorithm, prompt information

[1121] Output: Generated storyboard

[1122] Specific behavior:

[1123] Use GPT-3 to generate detailed scene descriptions based on prompt information.

[1124] Image generation techniques are used to create concrete scene images based on scene descriptions.

[1125] Integrate the scene description with the generated images to build a complete storyboard.

[1126] Step 6: Return the storyboard

[1127] The server returns the generated storyboard to the user's device as an API response, which is also in JSON format.

[1128] Input: Generated storyboard

[1129] Output: Storyboard data as API response

[1130] Specific behavior:

[1131] Convert the generated storyboard into JSON format.

[1132] As an API response, the storyboard is returned to the device in an HTTP response message.

[1133] Step 7: User review and editing

[1134] The user checks the storyboard displayed on the terminal and makes edits as necessary. Once editing is complete, the user clicks the final confirmation button to finalize the storyboard.

[1135] Input: Returned storyboard

[1136] Output: Finalized storyboard

[1137] Specific behavior:

[1138] Check the storyboard on the device's UI.

[1139] Add details or modify scenes and actions as needed.

[1140] Once you're done editing, click the "Final Confirm" button to finalize the storyboard.

[1141] (Application example 1)

[1142] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1143] Conventional storyboard generation systems can automatically generate storyboards based on prompt information entered by the user, but they have limited means for sharing the generated storyboards with other users. Furthermore, they lack an interface or means for users to easily edit the storyboards they generate and use them to create videos. Therefore, there is a need for a system that allows users to efficiently share generated storyboards and easily edit and use them.

[1144] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1145] In this invention, the server includes means for receiving a plurality of pieces of prompt information input by a user, means for analyzing the prompt information, means for selecting a generation algorithm based on the analysis result, means for generating a storyboard using the selected generation algorithm, means for returning the generated storyboard to the user, means for displaying and editing the returned storyboard, and means for sharing the generated storyboard with other users via a content sharing service. This enables users to efficiently share the generated storyboard with other users and use it for editing or video production.

[1146] "Prompt information" refers to information that a user inputs to generate a storyboard, specifically, titles, scenes, actions, and locations.

[1147] A "generation algorithm" is an algorithm that analyzes input prompt information and generates content such as storyboards based on that information, and primarily includes natural language processing technology and image generation technology.

[1148] A "storyboard" is a visual illustration that shows the elements and movements of each scene in order to plan and execute video production.

[1149] The "content sharing service" refers to a service via the Internet for sharing content such as created storyboards with other users.

[1150] "Parsing" refers to the process of understanding the input prompt information and selecting an appropriate generation algorithm.

[1151] "User" refers to a person or organization that uses the storyboard generation system.

[1152] This invention relates to a system that automatically generates storyboards based on prompt information entered by users, and allows them to be shared and edited. The system's program uses the Python language, Flask (a web framework), and the OpenAI API. The user's smartphone functions as the terminal, and the server is the backend that processes requests from users.

[1153] System configuration and operation

[1154] 1. User enters prompt

[1155] The user launches the smartphone application and logs in. The user presses a button to create a new project and fills in a form to enter prompt information based on the video idea. The prompt information includes the title, scene, action, and location. This information is sent from the user's device to the server.

[1156] 2. Parsing prompt information

[1157] The server receives the prompt information entered by the user and analyzes the content using natural language processing technology. Specifically, it uses a generative AI model such as OpenAI's GPT-3 to understand the meaning of the prompt information and select an appropriate generation algorithm.

[1158] 3. Storyboard generation

[1159] The server uses the selected generation algorithm to generate a storyboard based on the prompt information, which contains specific instructions for each scene and action in the video.

[1160] 4. Return and display of storyboards

[1161] The server returns the generated storyboard to the user's device, which receives the data returned as an API response and displays it on the user interface.

[1162] 5. User Editing and Sharing

[1163] The user can check the storyboard displayed on the device and edit it as necessary. Once edited, the storyboard can be shared with other users via a content sharing service.

[1164] Hardware and software used

[1165] Hardware: Smartphone (terminal) and server

[1166] Software: Python (programming language), Flask (web framework), OpenAI API (generative AI model)

[1167] Specific examples

[1168] For example, if a user enters the video idea "Morning yoga by a tranquil lake with a sunrise in the background" as a prompt, they would enter the following information:

[1169] Title: "Morning Yoga"

[1170] Scene: A calm lake with a sunrise in the background

[1171] Movement: Yoga pose

[1172] This prompt information is sent to the server in the following format:

[1173] Generate a storyboard: Title: "Morning Yoga", Scene: Calm lake with sunrise in the background, Action: Striking a yoga pose

[1174] The server parses this information and generates a storyboard like this:

[1175] 1. Scene 1: The sun begins to rise, revealing a tranquil scene over a lake.

[1176] 2. Scene 2: The protagonist lays out her yoga mat and begins getting ready.

[1177] 3. Scene 3: She is shown performing a yoga pose.

[1178] The generated storyboard is returned to the user and displayed on their device, where the user can edit it as needed and ultimately share it with other users via a content sharing service.

[1179] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1180] Step 1:

[1181] The user launches the smartphone application and logs in. They press the "Create a new project" button and fill out a form to enter prompt information based on their video idea. This information includes the title, scene, action, and location. The entered prompt information is temporarily saved on the device.

[1182] input:

[1183] Prompt information for user input (title, scene, action, location)

[1184] output:

[1185] Prompt information stored on the device

[1186] Step 2:

[1187] The device generates an API request to send the saved prompt information to the server and sends it to the server.

[1188] input:

[1189] Prompt information stored on the device

[1190] output:

[1191] API requests sent to the server

[1192] Step 3:

[1193] The server receives the API request and analyzes the sent prompt information. Using natural language processing technology, such as OpenAI's API, the server understands the content of the prompt information and selects the appropriate generation algorithm.

[1194] input:

[1195] API requests sent to the server

[1196] output:

[1197] Prompt information analysis results

[1198] Selected generation algorithm

[1199] Step 4:

[1200] The server uses a selected generation algorithm to generate a storyboard based on the prompt information, which contains specific instructions for each scene and action in the video.

[1201] input:

[1202] Prompt information analysis results

[1203] Selected generation algorithm

[1204] output:

[1205] Generated storyboard

[1206] Step 5:

[1207] The server sends the generated storyboard back to the user's device as an API response, and the device analyzes the received data and displays it on the user interface.

[1208] input:

[1209] Generated storyboard

[1210] output:

[1211] API response sent back to the device

[1212] Storyboard display on device

[1213] Step 6:

[1214] The user can check the storyboard displayed on the device and make edits as necessary. Once editing is complete, the storyboard is confirmed by pressing the final confirmation button.

[1215] input:

[1216] Storyboard displayed on the device

[1217] output:

[1218] User edited storyboard

[1219] Step 7:

[1220] The finalized storyboard can be shared with other users via a content sharing service. The server receives the share request and provides a share link to other users.

[1221] input:

[1222] Storyboard confirmed by user

[1223] output:

[1224] Storyboards shared through content sharing services

[1225] Shared link provided to other users

[1226] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1227] The present invention relates to a system that combines prompt information input by a user with an emotion engine that recognizes the user's emotions. Below, the processing of the system program and specific examples will be described.

[1228] System configuration and operation

[1229] 1. User enters prompt

[1230] The user launches the application on their device (e.g., PC or smartphone) and logs in. They click the "Create a new project" button and fill out a form to enter prompt information (title, scene, action, location, etc.) based on their video idea.

[1231] 2. Emotion recognition by emotion engine

[1232] The terminal operates an emotion engine that recognizes emotions from the user's facial expressions, voice, and input text while the user is entering prompt information. The emotion engine analyzes the user's current emotional state and transmits the results to the server.

[1233] 3. Sending prompt and emotional information

[1234] The terminal collects prompt information input by the user, generates an API request to be sent to the server together with emotion information obtained from the emotion engine, and sends the request to the server.

[1235] 4. Analysis of prompt information and emotional information

[1236] The server analyzes the received prompt and emotional information, understands the content using natural language processing and facial expression analysis technologies, and then selects the optimal generation algorithm (e.g., GPT-3 or image generation technology) based on the prompt and emotional information.

[1237] 5. Storyboard Generation

[1238] The server uses the selected generation algorithm to generate a storyboard based on the prompt information and the emotion information, which includes specific instructions for each scene and action in the video and elements that reflect the user's emotional state.

[1239] 6. Returning the storyboard

[1240] The server sends the generated storyboard back to the user's device as an API response, and the device analyzes the received data and displays it on the user interface.

[1241] 7. User Review and Editing

[1242] The user can check the storyboard displayed on the terminal and make edits as necessary. Once the storyboard has been edited, the user can confirm it by clicking the final confirmation button.

[1243] Specific examples

[1244] For example, let's say a user wants to create a short comedy video about a clumsy friend trying to give something they forgot in the school hallway. The user would enter the prompt information as follows:

[1245] Title: "Forgotten Things"

[1246] Scene: School hallway

[1247] Action: Handing something back to a friend, making a mistake

[1248] Location: School hallway

[1249] At the same time, the emotion engine analyzes the user's facial expressions and voice while inputting and recognizes that the user is in a happy emotional state. The device then transmits this prompt information and emotion information to the server.

[1250] The server analyzes the information and selects the appropriate generation algorithm, which generates the storyboard and outputs a storyboard containing the following scenes:

[1251] 1. Scene 1: In the school hallway, a friend comes running with something they forgot. They look happy.

[1252] 2. Scene 2: A friend slips and falls. Happy expressions and actions.

[1253] 3. Scene 3: The friend laughs and hands over the forgotten item.

[1254] The server sends the storyboard back to the device, where the user can review and edit it. For example, the user can add details about "why the friend fell" in Scene 2. Finally, once the user is satisfied with the storyboard, the video is shot.

[1255] In this way, the system of the present invention allows the user to easily create specific storyboards and efficiently proceed with the production of professional videos that reflect the user's emotions.

[1256] The processing flow will be explained below.

[1257] Step 1: User enters prompt information

[1258] The user starts the application on the terminal and logs in.

[1259] The user clicks the "Create a new project" button, which displays a form for entering prompt information.

[1260] The user enters information such as title, scene, action, location, etc. into the input fields and clicks the "Submit" button.

[1261] Step 2: The device activates the emotion engine

[1262] The terminal runs the emotion engine while the user is entering the prompt information.

[1263] The emotion engine uses a camera and microphone to analyze the user's facial expressions and voice in real time.

[1264] Step 3: The device sends prompt information and emotion information to the server.

[1265] The terminal collects the prompt information input by the user and combines it with the emotion information obtained from the emotion engine into one data packet.

[1266] The device generates an API request for transmitting the collected prompt information and emotion information to the server, and sends the request to the server.

[1267] Step 4: The server analyzes the prompt and emotion information

[1268] The server analyzes the received prompt information and emotion information.

[1269] The server uses natural language processing technology to analyze the content of the prompt information and uses the emotional information to understand the user's emotional state.

[1270] Based on the analysis results, the server selects the optimal generation algorithm based on prompt information and emotion information.

[1271] Step 5: The server generates the storyboard using a generation algorithm

[1272] The server uses a selected generation algorithm (e.g., GPT-3 or image generation technology) to generate a storyboard based on prompt information and emotion information.

[1273] The server creates a storyboard containing specific instructions for each scene and action, as well as elements that reflect the user's emotional state.

[1274] Step 6: The server sends the generated storyboard back to the device

[1275] The server prepares an API response to return the generated storyboard to the user's device.

[1276] The server executes the API response and sends the storyboard to the device.

[1277] Step 7: The device displays the storyboard, and the user checks and edits it.

[1278] The terminal analyzes the received storyboard data and displays it on the user interface.

[1279] The user checks the displayed storyboard and confirms the content of each scene and action.

[1280] The user edits the storyboard as needed and clicks the "Save" button.

[1281] Step 8: The device sends the edited storyboard to the server

[1282] The device generates an API request to send the storyboard that the user has edited and confirmed to the server.

[1283] The device executes an API request and sends the edited storyboard to the server.

[1284] Step 9: The server saves the final storyboard and notifies you that the confirmation is complete

[1285] The server stores the received final storyboard data in a database.

[1286] The server prepares an API response to notify the device that the final storyboard has been confirmed.

[1287] The server executes the API response and sends a confirmation completion notification to the terminal.

[1288] Through the above steps, users can efficiently create detailed storyboards and proceed with the production of professional videos that reflect emotions.

[1289] Example 2

[1290] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1291] Conventional storyboard generation systems have difficulty reflecting user emotions, and because they generate content based solely on prompt information, they lack the subtle nuances and emotional expression desired by users. Furthermore, users sometimes find it difficult to clearly communicate their emotions, which can result in generated content that deviates from the user's intentions. Therefore, there has been a demand for a system that generates storyboards that effectively reflect user emotions.

[1292] The specification processing by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving a plurality of pieces of prompt information input by the user, means for analyzing the prompt information, means for selecting a generation algorithm based on the analysis result, means for generating a storyboard using the selected generation algorithm, means for returning the generated storyboard to the user, means for displaying and editing the returned storyboard, means for detecting the user's emotions and analyzing the emotion information together with the prompt information, and means for including emotion-reflecting elements in a storyboard generated based on the analyzed emotion information. This makes it possible to generate a storyboard that reflects the user's emotions.

[1293] "Prompt information" is information based on the idea of ​​the video, such as title, scene, action, location, etc., entered by the user.

[1294] An "emotion engine" is software that detects emotions by analyzing a user's facial expressions, voice, input text, etc.

[1295] A "generation algorithm" is an algorithm used to generate a storyboard or the like based on prompt information and emotion information.

[1296] A "storyboard" is a visual storyboard that contains specific instructions for each scene and action in a video, as well as elements that reflect the user's emotional state.

[1297] The "server" is a computer system that analyzes prompt information and emotional information, selects a generation algorithm based on that information, generates a storyboard, and returns it to the terminal.

[1298] A "terminal" is a device, such as a personal computer or smartphone, through which a user inputs prompt information and checks and edits the generated storyboard.

[1299] "Analysis means" refers to a method or function for understanding received prompt information and emotion information and performing processing based on that information.

[1300] "Emotion-reflecting elements" are elements that are reflected in the storyboard based on the user's emotional information, and include, for example, the facial expressions and movements of characters.

[1301] "Natural language processing" is the technology that enables computers to understand and generate human language.

[1302] "Image generation technology" is a technology that allows computers to generate visual content.

[1303] The present invention relates to a system that combines prompt information input by a user with an emotion engine that recognizes the user's emotions. Below, the processing of the system program and specific examples will be described.

[1304] System configuration and operation

[1305] This system consists of three main components: the user, the device, and the server. The user inputs prompt information using the device, and the device analyzes the user's emotions using an emotion engine. The analyzed prompt information and emotion information are sent to the server, which then generates a storyboard based on this and sends it back to the device.

[1306] 1. User enters prompt

[1307] A user launches the application on a device (such as a PC or smartphone) and logs in. The user clicks the "Create a new project" button and enters prompt information based on their video idea, including title, scene, action, location, etc.

[1308] 2. Emotion recognition by emotion engine

[1309] The device activates an emotion engine to analyze the user's facial expressions, voice, and input text to determine their emotions. This emotion information reflects the user's current emotional state and is temporarily stored on the device along with the prompt information.

[1310] 3. Sending prompt and emotional information

[1311] The device sends the prompt information entered by the user and the emotion information analyzed by the emotion engine to the server via an API request.

[1312] 4. Analysis of prompt information and emotional information

[1313] The server analyzes the received prompt information and emotional information. Specifically, it uses natural language processing technology (e.g., GPT-3) and facial expression analysis technology to understand the content and emotion of the prompt. Based on the analysis results, it selects the optimal generation algorithm.

[1314] 5. Storyboard Generation

[1315] The server uses the selected generation algorithm to generate a storyboard based on the prompt information and the emotion information, which includes specific instructions for each scene and elements that reflect the user's emotional state.

[1316] 6. Returning the storyboard

[1317] The server returns the generated storyboard to the device as an API response, and the device displays the received storyboard on the user interface for the user to confirm.

[1318] 7. User Review and Editing

[1319] The user checks the displayed storyboard and makes edits as necessary. Once editing is complete, the user clicks the "Final Confirm" button to finalize the storyboard.

[1320] Specific examples

[1321] For example, let's say a user wants to create a short comedy video about a clumsy friend trying to give something they forgot in the school hallway. The user would enter the prompt information as follows:

[1322] Title: "Forgotten Things"

[1323] Scene: School hallway

[1324] Action: Handing something back to a friend, making a mistake

[1325] Location: School hallway

[1326] At the same time, the emotion engine analyzes the user's facial expressions and voice while inputting and recognizes that the user is in a happy emotional state. The device then transmits this prompt information and emotion information to the server.

[1327] The server analyzes the information and selects the appropriate generation algorithm, which generates a storyboard containing the following scenes:

[1328] 1. Scene 1: In the school hallway, a friend comes running with something they forgot. They look happy.

[1329] 2. Scene 2: A friend slips and falls. Happy expressions and actions.

[1330] 3. Scene 3: The friend laughs and hands over the forgotten item.

[1331] The server sends the storyboard back to the device, where the user can review and edit it. For example, the user can add details about "why the friend fell" in Scene 2. Finally, once the user is satisfied with the storyboard, the video is shot.

[1332] In this way, the system allows users to easily create specific storyboards and efficiently create professional videos that reflect the user's emotions.

[1333] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1334] Step 1:

[1335] The user launches the application on the terminal and logs in.

[1336] Input: User login information (username, password).

[1337] How it works: A user goes to a terminal, opens an application, and enters their username and password into the login form.

[1338] Output: The application dashboard screen is displayed.

[1339] Step 2:

[1340] User clicks the "Create a new project" button and fills in prompt information based on their video idea.

[1341] Input: Prompt information (title, scene, action, location).

[1342] Action: The user writes down their video idea in a form where they enter prompt information. For example, "Title: Lost Item, Scene: School Hallway, Action: Handing Over Lost Item to Friend, Making a Mistake, Location: School Hallway."

[1343] Output: The entered prompt information is temporarily saved on the terminal.

[1344] Step 3:

[1345] The device activates an emotion engine and analyzes emotions from the user's facial expressions, voice, and input text.

[1346] Input: User's facial expression data, voice data, input text.

[1347] How it works: The device uses a camera and microphone to record the user's facial expressions and voice, which are then analyzed by the emotion engine. For example, if the user is laughing happily, the emotion engine will detect "happiness."

[1348] Output: Generate emotional information (e.g., enjoyment) and temporarily store it on the device.

[1349] Step 4:

[1350] The terminal transmits prompt information and emotion information to the server.

[1351] Input: prompt information, emotion information.

[1352] How it works: The device collects this information, converts it into JSON format, and sends it to the server as an API request.

[1353] Output: The server receives the prompt information and emotion information.

[1354] Step 5:

[1355] The server analyzes the received prompt information and emotion information.

[1356] Input: Received prompt information, emotion information.

[1357] How it works: The server uses natural language processing technology (such as GPT-3) and facial expression analysis technology to analyze the content and sentiment of the prompt.

[1358] Output: Based on the analysis results, the optimal generative algorithm is selected (e.g., GPT-3 model).

[1359] Step 6:

[1360] The server uses a selected generation algorithm to generate a storyboard based on the prompt information and the emotion information.

[1361] Input: Parsed prompt information, sentiment information, selected generation algorithm.

[1362] How it works: The server uses GPT-3 to automatically generate a storyboard, for example, a storyboard containing scenes such as "Scene 1: School hallway, a friend comes running with something they forgot. Happy expression."

[1363] Output: Storyboard data is generated.

[1364] Step 7:

[1365] The server returns the generated storyboard to the terminal.

[1366] Input: The generated storyboard data.

[1367] Operation: The server sends the storyboard data to the device as an API response.

[1368] Output: The device receives the storyboard data.

[1369] Step 8:

[1370] The terminal displays the received storyboard on the user interface and allows the user to check it.

[1371] Input: Received storyboard data.

[1372] Action: The device parses the received data and displays it in its interface for the user to review.

[1373] Output: The generated storyboard is displayed to the user.

[1374] Step 9:

[1375] The user checks the displayed storyboard and makes edits as necessary.

[1376] Input: The displayed storyboard.

[1377] Action: The user edits the storyboard using a tablet pen or mouse. For example, adding "Why did my friend fall down?" in Scene 2. Once editing is complete, the user clicks the "Final Confirm" button to finalize the storyboard.

[1378] Output: Edited and finalized storyboard.

[1379] (Application example 2)

[1380] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1381] In modern society, users' meal choices vary greatly depending on their mood and emotions on that day. However, conventional food delivery services lack the ability to recommend dishes that take the user's emotional state into account. As a result, it is difficult for users to achieve sufficient satisfaction when choosing a meal. In particular, there is a need for food recommendations that accurately reflect the user's emotions.

[1382] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1383] In this invention, the server includes means for receiving a plurality of pieces of prompt information input by the user, means for analyzing the prompt information and emotion data, means for selecting a generation algorithm based on the analysis results, means for analyzing the emotion information obtained from the emotion engine, means for recommending an optimal dish based on the prompt information and emotion information, and means for returning the recommended dish to the user, thereby enabling recipe suggestions that comprehensively consider the user's emotional state.

[1384] "User-entered prompt information" refers to a number of pieces of information entered by a user to embody a specific request or idea, including title, scene, action, location, food request, etc.

[1385] "Means for analyzing prompt information" refers to a processing function for analyzing the input prompt information in detail and understanding the user's intentions and goals.

[1386] The "means for selecting a generation algorithm" is a processing mechanism for determining an optimal generation algorithm based on the analyzed prompt information and emotion data.

[1387] The "means for generating a storyboard using a selected generation algorithm" is a function that uses a selected generation algorithm to automatically generate a storyboard that serves as a blueprint for a video or image.

[1388] The "means for returning the generated storyboard to the user" refers to a means for transmitting the generated storyboard to the user's terminal so that it can be displayed and edited.

[1389] "Means for displaying and editing the returned storyboard" refers to a function that allows the user to display the received storyboard on the terminal and edit or modify it as necessary.

[1390] The "emotion engine" is an analysis engine that analyzes the user's voice data, text data, and facial expression image data to identify the user's current emotional state.

[1391] "Means for integrating emotional information into analysis results" refers to a function that combines emotional information obtained from the emotion engine with the analysis results of prompt information to achieve comprehensive understanding.

[1392] The "means for recommending the most suitable dish" is a function for suggesting a dish that matches the user's emotional state and request based on the analyzed prompt information and emotional information.

[1393] The "means for returning recommended dishes to the user" refers to a means for sending information about the selected dishes to the user's terminal and suggesting them to the user.

[1394] The present invention relates to a food delivery application that recommends dishes taking into account the emotional state of the user. Specific embodiments for implementing the present invention will be described below.

[1395] System configuration

[1396] This system consists of an application that runs on the user's device, such as a smartphone or PC, and an emotion engine and generation algorithm that runs on the server side.

[1397] procedure

[1398] 1. User enters prompt

[1399] The user launches the application and enters their meal preference as a prompt, for example, a request such as "I would like something light."

[1400] 2. Emotion recognition by emotion engine

[1401] The device collects the user's voice data, text data, and facial expression image data when prompting, and sends them to the emotion engine, which analyzes this data and identifies the user's current emotional state.

[1402] 3. Sending prompt and emotional information

[1403] The device sends the prompt information and analyzed emotion data to the server, which then selects a generation algorithm based on this information.

[1404] 4. Food Recommendations

[1405] The server-side algorithm analyzes prompt and emotion information to recommend the most suitable dish. For example, if a user feels tired and wants to refresh, it will recommend cold soba noodles or a refreshing salad.

[1406] 5. Returning Recommendations

[1407] The server returns recommended dish information to the user's terminal, and the user can order dishes based on this information.

[1408] Hardware and software used

[1409] Hardware: Smartphones, PCs

[1410] Software: Sentiment analysis API (Python library), food delivery API

[1411] Data format: JSON format, text data, audio data, image data

[1412] Specific examples

[1413] For example, consider a case where a user feels tired and wants to relax. The user inputs into the app, "I'm tired, I want to relax. I want to eat something refreshing." The emotion engine analyzes the user's voice and facial expressions to determine that the user wants to relax. Based on the results of the analysis on the server side, recommendations such as "cold soba noodles" or "refreshing salad" are sent back to the user.

[1414] This allows users to easily order the food that best suits their emotional state at the time.

[1415] Examples of prompt statements include "I would like to eat something light," "I would like some spicy Chinese food," and "I would like to eat a special dessert."

[1416] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1417] Step 1:

[1418] A user launches the application and inputs a desired dish as a prompt. For example, the user may input "I want something light." The prompt information input by the user is collected in an input field of the application. The input data includes the user's request.

[1419] Step 2:

[1420] The device collects the user's voice data, text data, and facial expression image data. It prepares to send this data to the emotion engine. The collected data includes voice files (e.g., "I'm tired, I want to calm down"), text data, and image files (user's facial expressions).

[1421] Step 3:

[1422] The emotion engine analyzes the collected voice data, text data, and facial expression image data. From this data, the emotion engine identifies the user's current emotional state. Specifically, it uses voice analysis, text analysis, and image analysis algorithms to generate an emotional status, such as "I want to relax." The analysis results are output as emotional information.

[1423] Step 4:

[1424] The device sends prompt information and emotional information, which is the analysis result of the emotion engine, to the server. The sent data includes the user's cooking request (prompt information) and emotional data obtained through analysis, such as "I want to relax."

[1425] Step 5:

[1426] The server analyzes the prompt information and emotional information it receives. It uses natural language processing and facial expression analysis technologies to understand the user's input and emotions. Based on these results, it selects the optimal generation algorithm. For example, if the emotion is relaxed, it determines that a light dish would be appropriate. The input for the analysis is the prompt information and emotional data, and the output is the analysis result based on the selected algorithm.

[1427] Step 6:

[1428] The server uses a selected generation algorithm to recommend the best dish based on prompt and emotion information. During this generation process, dishes that match the criteria are extracted from a specific food database and selected as final candidates. The output includes dish candidates such as "cold soba noodles" and "refreshing salad."

[1429] Step 7:

[1430] The server sends the recommended dishes back to the user's device, which then displays the received dish information on the application's user interface. The user can then select from the dishes presented and confirm their order.

[1431] Step 8:

[1432] The user finally selects the food they want to order and confirms the order. By pressing the confirm button, the food ordering process is completed. The food selected by the user is sent as order data, and the food delivery service begins the process of delivering the food.

[1433] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1434] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1435] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1436] [Fourth embodiment]

[1437] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1438] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1439] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1440] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1441] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1442] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1443] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1444] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1445] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1446] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1447] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1448] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1449] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1450] The present invention relates to a system for automatically generating storyboards based on prompt information entered by a user. The following describes the program processing and specific examples of the system.

[1451] System configuration and operation

[1452] 1. User enters prompt

[1453] The user launches the application on their device (e.g., PC or smartphone) and logs in. They click the "Create a new project" button and fill out a form to enter prompt information (title, scene, action, location, etc.) based on their video idea.

[1454] 2. Sending prompt information

[1455] The terminal collects the prompt information input by the user, generates an API request to transmit the information to the server, and transmits the request to the server.

[1456] 3. Parsing prompt information

[1457] The server analyzes the received prompt information, understands the content using natural language processing technology, and then selects the optimal generation algorithm (e.g., GPT-3 or image generation technology) based on the prompt information.

[1458] 4. Storyboard generation

[1459] The server uses a selected generation algorithm to generate a storyboard based on the prompt information, which contains specific instructions for each scene and action in the video.

[1460] 5. Returning the storyboard

[1461] The server sends the generated storyboard back to the user's device as an API response, and the device analyzes the received data and displays it on the user interface.

[1462] 6. User Review and Editing

[1463] The user can check the storyboard displayed on the terminal and make edits as necessary. Once the storyboard has been edited, the user can confirm it by clicking the final confirmation button.

[1464] Specific examples

[1465] For example, let's say a user wants to create a short comedy video about "making a mistake while trying to give something to a friend in the school hallway." The user would enter the prompt information as follows:

[1466] Title: "Forgotten Things"

[1467] Scene: School hallway

[1468] Action: Handing something back to a friend, making a mistake

[1469] Location: School hallway

[1470] The device sends these prompts to the server, which analyzes the information and selects an appropriate generation algorithm. The generation algorithm generates a storyboard, and the output is a storyboard containing the following scenes:

[1471] 1. Scene 1: In the school hallway, a friend comes running with something they forgot.

[1472] 2. Scene 2: Your friend slips and falls.

[1473] 3. Scene 3: The friend laughs and hands over the forgotten item.

[1474] The storyboard is sent back to the device from the server, where the user can review and edit it. For example, the user can add details about "why the friend fell" in Scene 2. Finally, the storyboard is finalized to the user's satisfaction, and the video is shot based on it.

[1475] In this way, the system of the present invention allows users to easily create specific storyboards and efficiently proceed with professional video production.

[1476] The processing flow will be explained below.

[1477] Step 1: User enters prompt information

[1478] The user starts the application on the terminal and logs in.

[1479] The user clicks the "Create a new project" button, which displays a form for entering prompt information.

[1480] The user enters information such as title, scene, action, location, etc. into the input fields and clicks the "Submit" button.

[1481] Step 2: The device sends the prompt information to the server

[1482] The terminal collects the prompt information entered by the user.

[1483] The device generates an API request to send the collected prompt information to the server.

[1484] The device executes an API request and sends the prompt information to the server.

[1485] Step 3: The server parses the prompt information

[1486] The server uses natural language processing techniques to parse the received prompt information.

[1487] The server interprets the contents of the prompt information and selects a generation algorithm based on the analysis results.

[1488] Step 4: The server generates the storyboard using a generation algorithm

[1489] The server generates the storyboard using a selected generation algorithm (e.g., GPT-3 or image generation technology).

[1490] Based on the prompt information, the server creates a storyboard containing specific instructions for each scene and action.

[1491] Step 5: The server sends the generated storyboard back to the device

[1492] The server prepares an API response to send the generated storyboard to the user's device.

[1493] The server executes the API response and sends the storyboard to the device.

[1494] Step 6: The device displays the storyboard, and the user checks and edits it.

[1495] The terminal analyzes the received storyboard data and displays it on the user interface.

[1496] The user can check the displayed storyboard and edit each scene and action as necessary.

[1497] When the user has finished editing, he clicks the "Save" button.

[1498] Step 7: The device sends the edited storyboard to the server

[1499] The device generates an API request to send the storyboard that the user has edited and confirmed to the server.

[1500] The device executes an API request and sends the edited storyboard to the server.

[1501] Step 8: The server saves the final storyboard and notifies you that the confirmation is complete

[1502] The server stores the received final storyboard data in a database.

[1503] The server prepares an API response to notify the device that the final storyboard has been confirmed.

[1504] The server executes the API response and sends a confirmation completion notification to the terminal.

[1505] By following the steps above, users can efficiently generate concrete storyboards and use them as a guide for video production.

[1506] Example 1

[1507] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1508] In conventional video production, creating storyboards requires specialized knowledge and effort, making it difficult for beginners and general users. Furthermore, creating storyboards manually takes time and effort, hindering efficient video production. Therefore, there has been a demand for a system that allows users to easily and efficiently create and edit storyboards.

[1509] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1510] In this invention, the server includes means for transmitting prompt information from the user's terminal to the server, means for the server to analyze the prompt information using natural language processing technology, and means for the server to select an optimal generation algorithm using the natural language processing technology. This makes it possible to efficiently generate a specific storyboard based on the prompt information entered by the user and return the storyboard to the user.

[1511] "Prompt information" is information that a user inputs based on an idea for a video, and includes details such as title, scenes, actions, and locations.

[1512] The "means for analyzing" is a function for understanding and analyzing the content of the prompt information received by the server using natural language processing technology.

[1513] The "generation algorithm" is an algorithm used to generate a storyboard based on prompt information, and specifically includes natural language processing technology and image generation technology.

[1514] A "storyboard" is a visual sketch or depiction that contains specific instructions for each scene or action in a video.

[1515] The "means for returning" is a function for returning the storyboard generated by the server to the user's device, and is performed as an API response.

[1516] The "display and editing means" refers to an interface and functions that allow the received storyboard to be displayed on the user terminal and for the user to edit it as needed.

[1517] "Natural language processing technology" is a technology that enables computers to understand and analyze human language, and is used to select generation algorithms and analyze prompt information.

[1518] "Image generation technology" refers to technology that allows a computer to generate images based on prompt information, creating a concrete visual representation of the storyboard.

[1519] An "API request" is a communication request from a user terminal to a server to request the operation of a specific service, and is used when sending prompt information.

[1520] An "API response" is response data returned from the server to the user terminal, and includes the generated storyboard.

[1521] The present invention relates to a system for automatically generating storyboards based on prompt information entered by a user. The program processing of the system and an embodiment thereof will be specifically described below.

[1522] System configuration

[1523] The system uses user terminals, servers, and API requests and responses to communicate between them.

[1524] 1. User enters prompt

[1525] The user launches the application on their device (such as a PC or smartphone) and logs in. After logging in, the user clicks the "Create a new project" button and enters information into a form for entering prompt information (such as title, scene, action, location, etc.). This prompt information is used to generate a storyboard.

[1526] Software used: Web application, mobile application

[1527] 2. Sending prompt information

[1528] The terminal collects the prompt information entered by the user and generates an API request as JSON formatted data, which is then sent to the server using the HTTP POST method.

[1529] Technologies used: RESTful API, JSON data format

[1530] 3. Parsing prompt information

[1531] The server analyzes the received prompt information using natural language processing technology. Specifically, it uses a natural language processing engine (e.g., NLTK or Spacy) to analyze the prompt information and understand its content. Based on the analysis results, it selects the optimal generation algorithm (e.g., the generative AI model GPT-3 or image generation technology).

[1532] Software used: NLTK, Spacy, GPT-3

[1533] 4. Storyboard generation

[1534] The server uses the selected generation algorithm to generate a storyboard based on the prompt information. Specifically, it uses GPT-3 to generate detailed scene descriptions and image generation technology to create specific scene images. These are then combined to create the storyboard.

[1535] Technologies used: GPT-3, image generation technology

[1536] 5. Returning the storyboard

[1537] The server returns the generated storyboard to the user's device as an API response, which is also in JSON format.

[1538] Technologies used: RESTful API, JSON data format

[1539] 6. User Review and Editing

[1540] The user can check the storyboard displayed on the terminal and make edits as necessary. Once editing is complete, the user clicks the final confirmation button to finalize the storyboard.

[1541] Software used: Web application, mobile application

[1542] Specific examples

[1543] As an example, suppose a user wants to create a short comedy video about "making a mistake while trying to give something to a friend in the school hallway."

[1544] Example of user prompt input

[1545] Title: "Forgotten Things"

[1546] Scene: School hallway

[1547] Action: Handing something back to a friend, making a mistake

[1548] Location: School hallway

[1549] The user inputs this information into the application, and the device sends it to the server. The server analyzes the information and selects an appropriate generation algorithm. The generation algorithm generates a storyboard containing the following scenes:

[1550] 1. Scene 1: In the school hallway, a friend comes running with something they forgot.

[1551] 2. Scene 2: Your friend slips and falls.

[1552] 3. Scene 3: The friend laughs and hands over the forgotten item.

[1553] The server sends the storyboard back to the device, where the user can review and edit it. For example, the user can add details about "why the friend fell" in Scene 2.

[1554] In this way, the system of the present invention enables efficient video production by allowing users to easily create and edit specific storyboards.

[1555] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1556] Step 1: User Enters Prompt

[1557] The user launches the application on their device (PC, smartphone, etc.) and logs in. After logging in, they click the "Create a new project" button and enter the prompt information (title, scene, action, location, etc.) in the form.

[1558] Input: Prompt information entered by the user (title, scene, action, location)

[1559] Output: The prompt information entered is saved in the form

[1560] Specific behavior:

[1561] Start the application and enter your user ID and password in the login form.

[1562] After logging in, on the dashboard screen, click the "Create a new project" button.

[1563] In the form that appears, enter the title "Forgotten Item," the scene "School Hallway," the action "Giving forgotten item to friend, making a mistake," and the location "School Hallway."

[1564] Step 2: Send prompt information

[1565] The terminal collects the prompt information entered by the user and generates an API request, which is then sent to the server using the HTTP POST method.

[1566] Input: The prompt information entered by the user.

[1567] Output: The generated API request is sent to the server.

[1568] Specific behavior:

[1569] Collect prompt information as JSON format data and generate an API request.

[1570] Send an API request to the server using the HTTP POST method.

[1571] Wait for a response from the server.

[1572] Step 3: Parse prompt information

[1573] The server analyzes the received prompt information using natural language processing technology. Specifically, it uses a natural language processing engine (such as NLTK or Spacy) to analyze the prompt information and understand its content.

[1574] Input: Received prompt information

[1575] Output: Analysis results (understanding the contents of prompt information)

[1576] Specific behavior:

[1577] The server receives the API request.

[1578] The received prompt information is analyzed using a natural language processing engine.

[1579] As a result of the analysis, data that understands the content of the prompt information is generated.

[1580] Step 4: Selecting a generation algorithm

[1581] The server selects the optimal generation algorithm (e.g., GPT-3 or image generation technology) based on the analysis results.

[1582] Input: Analysis result of prompt information

[1583] Output: The selected generation algorithm

[1584] Specific behavior:

[1585] Based on the analysis results of the prompt information, candidate generation algorithms are evaluated.

[1586] The most suitable algorithm is selected from among those such as GPT-3 and image generation technology.

[1587] Record the selected generation algorithm.

[1588] Step 5: Generate the storyboard

[1589] The server uses the selected generation algorithm to generate a storyboard based on the prompt information. Specifically, it uses GPT-3 to generate detailed scene descriptions and image generation technology to create specific scene images. These are then combined to create the storyboard.

[1590] Input: Selected generation algorithm, prompt information

[1591] Output: Generated storyboard

[1592] Specific behavior:

[1593] Use GPT-3 to generate detailed scene descriptions based on prompt information.

[1594] Image generation techniques are used to create concrete scene images based on scene descriptions.

[1595] Integrate the scene description with the generated images to build a complete storyboard.

[1596] Step 6: Return the storyboard

[1597] The server returns the generated storyboard to the user's device as an API response, which is also in JSON format.

[1598] Input: Generated storyboard

[1599] Output: Storyboard data as API response

[1600] Specific behavior:

[1601] Convert the generated storyboard into JSON format.

[1602] As an API response, the storyboard is returned to the device in an HTTP response message.

[1603] Step 7: User review and editing

[1604] The user checks the storyboard displayed on the terminal and makes edits as necessary. Once editing is complete, the user clicks the final confirmation button to finalize the storyboard.

[1605] Input: Returned storyboard

[1606] Output: Finalized storyboard

[1607] Specific behavior:

[1608] Check the storyboard on the device's UI.

[1609] Add details or modify scenes and actions as needed.

[1610] Once you're done editing, click the "Final Confirm" button to finalize the storyboard.

[1611] (Application example 1)

[1612] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1613] Conventional storyboard generation systems can automatically generate storyboards based on prompt information entered by the user, but they have limited means for sharing the generated storyboards with other users. Furthermore, they lack an interface or means for users to easily edit the storyboards they generate and use them to create videos. Therefore, there is a need for a system that allows users to efficiently share generated storyboards and easily edit and use them.

[1614] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1615] In this invention, the server includes means for receiving a plurality of pieces of prompt information input by a user, means for analyzing the prompt information, means for selecting a generation algorithm based on the analysis result, means for generating a storyboard using the selected generation algorithm, means for returning the generated storyboard to the user, means for displaying and editing the returned storyboard, and means for sharing the generated storyboard with other users via a content sharing service. This enables users to efficiently share the generated storyboard with other users and use it for editing or video production.

[1616] "Prompt information" refers to information that a user inputs to generate a storyboard, specifically, titles, scenes, actions, and locations.

[1617] A "generation algorithm" is an algorithm that analyzes input prompt information and generates content such as storyboards based on that information, and primarily includes natural language processing technology and image generation technology.

[1618] A "storyboard" is a visual illustration that shows the elements and movements of each scene in order to plan and execute video production.

[1619] The "content sharing service" refers to a service via the Internet for sharing content such as created storyboards with other users.

[1620] "Parsing" refers to the process of understanding the input prompt information and selecting an appropriate generation algorithm.

[1621] "User" refers to a person or organization that uses the storyboard generation system.

[1622] This invention relates to a system that automatically generates storyboards based on prompt information entered by users, and allows them to be shared and edited. The system's program uses the Python language, Flask (a web framework), and the OpenAI API. The user's smartphone functions as the terminal, and the server is the backend that processes requests from users.

[1623] System configuration and operation

[1624] 1. User enters prompt

[1625] The user launches the smartphone application and logs in. The user presses a button to create a new project and fills in a form to enter prompt information based on the video idea. The prompt information includes the title, scene, action, and location. This information is sent from the user's device to the server.

[1626] 2. Parsing prompt information

[1627] The server receives the prompt information entered by the user and analyzes the content using natural language processing technology. Specifically, it uses a generative AI model such as OpenAI's GPT-3 to understand the meaning of the prompt information and select an appropriate generation algorithm.

[1628] 3. Storyboard generation

[1629] The server uses the selected generation algorithm to generate a storyboard based on the prompt information, which contains specific instructions for each scene and action in the video.

[1630] 4. Return and display of storyboards

[1631] The server returns the generated storyboard to the user's device, which receives the data returned as an API response and displays it on the user interface.

[1632] 5. User Editing and Sharing

[1633] The user can check the storyboard displayed on the device and edit it as necessary. Once edited, the storyboard can be shared with other users via a content sharing service.

[1634] Hardware and software used

[1635] Hardware: Smartphone (terminal) and server

[1636] Software: Python (programming language), Flask (web framework), OpenAI API (generative AI model)

[1637] Specific examples

[1638] For example, if a user enters the video idea "Morning yoga by a tranquil lake with a sunrise in the background" as a prompt, they would enter the following information:

[1639] Title: "Morning Yoga"

[1640] Scene: A calm lake with a sunrise in the background

[1641] Movement: Yoga pose

[1642] This prompt information is sent to the server in the following format:

[1643] Generate a storyboard: Title: "Morning Yoga", Scene: Calm lake with sunrise in the background, Action: Striking a yoga pose

[1644] The server parses this information and generates a storyboard like this:

[1645] 1. Scene 1: The sun begins to rise, revealing a tranquil scene over a lake.

[1646] 2. Scene 2: The protagonist lays out her yoga mat and begins getting ready.

[1647] 3. Scene 3: She is shown performing a yoga pose.

[1648] The generated storyboard is returned to the user and displayed on their device, where the user can edit it as needed and ultimately share it with other users via a content sharing service.

[1649] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1650] Step 1:

[1651] The user launches the smartphone application and logs in. They press the "Create a new project" button and fill out a form to enter prompt information based on their video idea. This information includes the title, scene, action, and location. The entered prompt information is temporarily saved on the device.

[1652] input:

[1653] Prompt information for user input (title, scene, action, location)

[1654] output:

[1655] Prompt information stored on the device

[1656] Step 2:

[1657] The device generates an API request to send the saved prompt information to the server and sends it to the server.

[1658] input:

[1659] Prompt information stored on the device

[1660] output:

[1661] API requests sent to the server

[1662] Step 3:

[1663] The server receives the API request and analyzes the sent prompt information. Using natural language processing technology, such as OpenAI's API, the server understands the content of the prompt information and selects the appropriate generation algorithm.

[1664] input:

[1665] API requests sent to the server

[1666] output:

[1667] Prompt information analysis results

[1668] Selected generation algorithm

[1669] Step 4:

[1670] The server uses a selected generation algorithm to generate a storyboard based on the prompt information, which contains specific instructions for each scene and action in the video.

[1671] input:

[1672] Prompt information analysis results

[1673] Selected generation algorithm

[1674] output:

[1675] Generated storyboard

[1676] Step 5:

[1677] The server sends the generated storyboard back to the user's device as an API response, and the device analyzes the received data and displays it on the user interface.

[1678] input:

[1679] Generated storyboard

[1680] output:

[1681] API response sent back to the device

[1682] Storyboard display on device

[1683] Step 6:

[1684] The user can check the storyboard displayed on the device and make edits as necessary. Once editing is complete, the storyboard is confirmed by pressing the final confirmation button.

[1685] input:

[1686] Storyboard displayed on the device

[1687] output:

[1688] User edited storyboard

[1689] Step 7:

[1690] The finalized storyboard can be shared with other users via a content sharing service. The server receives the share request and provides a share link to other users.

[1691] input:

[1692] Storyboard confirmed by user

[1693] output:

[1694] Storyboards shared through content sharing services

[1695] Shared link provided to other users

[1696] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1697] The present invention relates to a system that combines prompt information input by a user with an emotion engine that recognizes the user's emotions. Below, the processing of the system program and specific examples will be described.

[1698] System configuration and operation

[1699] 1. User enters prompt

[1700] The user launches the application on their device (e.g., PC or smartphone) and logs in. They click the "Create a new project" button and fill out a form to enter prompt information (title, scene, action, location, etc.) based on their video idea.

[1701] 2. Emotion recognition by emotion engine

[1702] The terminal operates an emotion engine that recognizes emotions from the user's facial expressions, voice, and input text while the user is entering prompt information. The emotion engine analyzes the user's current emotional state and transmits the results to the server.

[1703] 3. Sending prompt and emotional information

[1704] The terminal collects prompt information input by the user, generates an API request to be sent to the server together with emotion information obtained from the emotion engine, and sends the request to the server.

[1705] 4. Analysis of prompt information and emotional information

[1706] The server analyzes the received prompt and emotional information, understands the content using natural language processing and facial expression analysis technologies, and then selects the optimal generation algorithm (e.g., GPT-3 or image generation technology) based on the prompt and emotional information.

[1707] 5. Storyboard Generation

[1708] The server uses the selected generation algorithm to generate a storyboard based on the prompt information and the emotion information, which includes specific instructions for each scene and action in the video and elements that reflect the user's emotional state.

[1709] 6. Returning the storyboard

[1710] The server sends the generated storyboard back to the user's device as an API response, and the device analyzes the received data and displays it on the user interface.

[1711] 7. User Review and Editing

[1712] The user can check the storyboard displayed on the terminal and make edits as necessary. Once the storyboard has been edited, the user can confirm it by clicking the final confirmation button.

[1713] Specific examples

[1714] For example, let's say a user wants to create a short comedy video about a clumsy friend trying to give something they forgot in the school hallway. The user would enter the prompt information as follows:

[1715] Title: "Forgotten Things"

[1716] Scene: School hallway

[1717] Action: Handing something back to a friend, making a mistake

[1718] Location: School hallway

[1719] At the same time, the emotion engine analyzes the user's facial expressions and voice while inputting and recognizes that the user is in a happy emotional state. The device then transmits this prompt information and emotion information to the server.

[1720] The server analyzes the information and selects the appropriate generation algorithm, which generates the storyboard and outputs a storyboard containing the following scenes:

[1721] 1. Scene 1: In the school hallway, a friend comes running with something they forgot. They look happy.

[1722] 2. Scene 2: A friend slips and falls. Happy expressions and actions.

[1723] 3. Scene 3: The friend laughs and hands over the forgotten item.

[1724] The server sends the storyboard back to the device, where the user can review and edit it. For example, the user can add details about "why the friend fell" in Scene 2. Finally, once the user is satisfied with the storyboard, the video is shot.

[1725] In this way, the system of the present invention allows the user to easily create specific storyboards and efficiently proceed with the production of professional videos that reflect the user's emotions.

[1726] The processing flow will be explained below.

[1727] Step 1: User enters prompt information

[1728] The user starts the application on the terminal and logs in.

[1729] The user clicks the "Create a new project" button, which displays a form for entering prompt information.

[1730] The user enters information such as title, scene, action, location, etc. into the input fields and clicks the "Submit" button.

[1731] Step 2: The device activates the emotion engine

[1732] The terminal runs the emotion engine while the user is entering the prompt information.

[1733] The emotion engine uses a camera and microphone to analyze the user's facial expressions and voice in real time.

[1734] Step 3: The device sends prompt information and emotion information to the server.

[1735] The terminal collects the prompt information input by the user and combines it with the emotion information obtained from the emotion engine into one data packet.

[1736] The device generates an API request for transmitting the collected prompt information and emotion information to the server, and sends the request to the server.

[1737] Step 4: The server analyzes the prompt and emotion information

[1738] The server analyzes the received prompt information and emotion information.

[1739] The server uses natural language processing technology to analyze the content of the prompt information and uses the emotional information to understand the user's emotional state.

[1740] Based on the analysis results, the server selects the optimal generation algorithm based on prompt information and emotion information.

[1741] Step 5: The server generates the storyboard using a generation algorithm

[1742] The server uses a selected generation algorithm (e.g., GPT-3 or image generation technology) to generate a storyboard based on prompt information and emotion information.

[1743] The server creates a storyboard containing specific instructions for each scene and action, as well as elements that reflect the user's emotional state.

[1744] Step 6: The server sends the generated storyboard back to the device

[1745] The server prepares an API response to return the generated storyboard to the user's device.

[1746] The server executes the API response and sends the storyboard to the device.

[1747] Step 7: The device displays the storyboard, and the user checks and edits it.

[1748] The terminal analyzes the received storyboard data and displays it on the user interface.

[1749] The user checks the displayed storyboard and confirms the content of each scene and action.

[1750] The user edits the storyboard as needed and clicks the "Save" button.

[1751] Step 8: The device sends the edited storyboard to the server

[1752] The device generates an API request to send the storyboard that the user has edited and confirmed to the server.

[1753] The device executes an API request and sends the edited storyboard to the server.

[1754] Step 9: The server saves the final storyboard and notifies you that the confirmation is complete

[1755] The server stores the received final storyboard data in a database.

[1756] The server prepares an API response to notify the device that the final storyboard has been confirmed.

[1757] The server executes the API response and sends a confirmation completion notification to the terminal.

[1758] Through the above steps, users can efficiently create detailed storyboards and proceed with the production of professional videos that reflect emotions.

[1759] Example 2

[1760] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1761] Conventional storyboard generation systems have difficulty reflecting user emotions, and because they generate content based solely on prompt information, they lack the subtle nuances and emotional expression desired by users. Furthermore, users sometimes find it difficult to clearly communicate their emotions, which can result in generated content that deviates from the user's intentions. Therefore, there has been a demand for a system that generates storyboards that effectively reflect user emotions.

[1762] The specification processing by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving a plurality of pieces of prompt information input by the user, means for analyzing the prompt information, means for selecting a generation algorithm based on the analysis result, means for generating a storyboard using the selected generation algorithm, means for returning the generated storyboard to the user, means for displaying and editing the returned storyboard, means for detecting the user's emotions and analyzing the emotion information together with the prompt information, and means for including emotion-reflecting elements in a storyboard generated based on the analyzed emotion information. This makes it possible to generate a storyboard that reflects the user's emotions.

[1763] "Prompt information" is information based on the idea of ​​the video, such as title, scene, action, location, etc., entered by the user.

[1764] An "emotion engine" is software that detects emotions by analyzing a user's facial expressions, voice, input text, etc.

[1765] A "generation algorithm" is an algorithm used to generate a storyboard or the like based on prompt information and emotion information.

[1766] A "storyboard" is a visual storyboard that contains specific instructions for each scene and action in a video, as well as elements that reflect the user's emotional state.

[1767] The "server" is a computer system that analyzes prompt information and emotional information, selects a generation algorithm based on that information, generates a storyboard, and returns it to the terminal.

[1768] A "terminal" is a device, such as a personal computer or smartphone, through which a user inputs prompt information and checks and edits the generated storyboard.

[1769] "Analysis means" refers to a method or function for understanding received prompt information and emotion information and performing processing based on that information.

[1770] "Emotion-reflecting elements" are elements that are reflected in the storyboard based on the user's emotional information, and include, for example, the facial expressions and movements of characters.

[1771] "Natural language processing" is the technology that enables computers to understand and generate human language.

[1772] "Image generation technology" is a technology that allows computers to generate visual content.

[1773] The present invention relates to a system that combines prompt information input by a user with an emotion engine that recognizes the user's emotions. Below, the processing of the system program and specific examples will be described.

[1774] System configuration and operation

[1775] This system consists of three main components: the user, the device, and the server. The user inputs prompt information using the device, and the device analyzes the user's emotions using an emotion engine. The analyzed prompt information and emotion information are sent to the server, which then generates a storyboard based on this and sends it back to the device.

[1776] 1. User enters prompt

[1777] A user launches the application on a device (such as a PC or smartphone) and logs in. The user clicks the "Create a new project" button and enters prompt information based on their video idea, including title, scene, action, location, etc.

[1778] 2. Emotion recognition by emotion engine

[1779] The device activates an emotion engine to analyze the user's facial expressions, voice, and input text to determine their emotions. This emotion information reflects the user's current emotional state and is temporarily stored on the device along with the prompt information.

[1780] 3. Sending prompt and emotional information

[1781] The device sends the prompt information entered by the user and the emotion information analyzed by the emotion engine to the server via an API request.

[1782] 4. Analysis of prompt information and emotional information

[1783] The server analyzes the received prompt information and emotional information. Specifically, it uses natural language processing technology (e.g., GPT-3) and facial expression analysis technology to understand the content and emotion of the prompt. Based on the analysis results, it selects the optimal generation algorithm.

[1784] 5. Storyboard Generation

[1785] The server uses the selected generation algorithm to generate a storyboard based on the prompt information and the emotion information, which includes specific instructions for each scene and elements that reflect the user's emotional state.

[1786] 6. Returning the storyboard

[1787] The server returns the generated storyboard to the device as an API response, and the device displays the received storyboard on the user interface for the user to confirm.

[1788] 7. User Review and Editing

[1789] The user checks the displayed storyboard and makes edits as necessary. Once editing is complete, the user clicks the "Final Confirm" button to finalize the storyboard.

[1790] Specific examples

[1791] For example, let's say a user wants to create a short comedy video about a clumsy friend trying to give something they forgot in the school hallway. The user would enter the prompt information as follows:

[1792] Title: "Forgotten Things"

[1793] Scene: School hallway

[1794] Action: Handing something back to a friend, making a mistake

[1795] Location: School hallway

[1796] At the same time, the emotion engine analyzes the user's facial expressions and voice while inputting and recognizes that the user is in a happy emotional state. The device then transmits this prompt information and emotion information to the server.

[1797] The server analyzes the information and selects the appropriate generation algorithm, which generates a storyboard containing the following scenes:

[1798] 1. Scene 1: In the school hallway, a friend comes running with something they forgot. They look happy.

[1799] 2. Scene 2: A friend slips and falls. Happy expressions and actions.

[1800] 3. Scene 3: The friend laughs and hands over the forgotten item.

[1801] The server sends the storyboard back to the device, where the user can review and edit it. For example, the user can add details about "why the friend fell" in Scene 2. Finally, once the user is satisfied with the storyboard, the video is shot.

[1802] In this way, the system allows users to easily create specific storyboards and efficiently create professional videos that reflect the user's emotions.

[1803] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1804] Step 1:

[1805] The user launches the application on the terminal and logs in.

[1806] Input: User login information (username, password).

[1807] How it works: A user goes to a terminal, opens an application, and enters their username and password into the login form.

[1808] Output: The application dashboard screen is displayed.

[1809] Step 2:

[1810] User clicks the "Create a new project" button and fills in prompt information based on their video idea.

[1811] Input: Prompt information (title, scene, action, location).

[1812] Action: The user writes down their video idea in a form where they enter prompt information. For example, "Title: Lost Item, Scene: School Hallway, Action: Handing Over Lost Item to Friend, Making a Mistake, Location: School Hallway."

[1813] Output: The entered prompt information is temporarily saved on the terminal.

[1814] Step 3:

[1815] The device activates an emotion engine and analyzes emotions from the user's facial expressions, voice, and input text.

[1816] Input: User's facial expression data, voice data, input text.

[1817] How it works: The device uses a camera and microphone to record the user's facial expressions and voice, which are then analyzed by the emotion engine. For example, if the user is laughing happily, the emotion engine will detect "happiness."

[1818] Output: Generate emotional information (e.g., enjoyment) and temporarily store it on the device.

[1819] Step 4:

[1820] The terminal transmits prompt information and emotion information to the server.

[1821] Input: prompt information, emotion information.

[1822] How it works: The device collects this information, converts it into JSON format, and sends it to the server as an API request.

[1823] Output: The server receives the prompt information and emotion information.

[1824] Step 5:

[1825] The server analyzes the received prompt information and emotion information.

[1826] Input: Received prompt information, emotion information.

[1827] How it works: The server uses natural language processing technology (such as GPT-3) and facial expression analysis technology to analyze the content and sentiment of the prompt.

[1828] Output: Based on the analysis results, the optimal generative algorithm is selected (e.g., GPT-3 model).

[1829] Step 6:

[1830] The server uses a selected generation algorithm to generate a storyboard based on the prompt information and the emotion information.

[1831] Input: Parsed prompt information, sentiment information, selected generation algorithm.

[1832] How it works: The server uses GPT-3 to automatically generate a storyboard, for example, a storyboard containing scenes such as "Scene 1: School hallway, a friend comes running with something they forgot. Happy expression."

[1833] Output: Storyboard data is generated.

[1834] Step 7:

[1835] The server returns the generated storyboard to the terminal.

[1836] Input: The generated storyboard data.

[1837] Operation: The server sends the storyboard data to the device as an API response.

[1838] Output: The device receives the storyboard data.

[1839] Step 8:

[1840] The terminal displays the received storyboard on the user interface and allows the user to check it.

[1841] Input: Received storyboard data.

[1842] Action: The device parses the received data and displays it in its interface for the user to review.

[1843] Output: The generated storyboard is displayed to the user.

[1844] Step 9:

[1845] The user checks the displayed storyboard and makes edits as necessary.

[1846] Input: The displayed storyboard.

[1847] Action: The user edits the storyboard using a tablet pen or mouse. For example, adding "Why did my friend fall down?" in Scene 2. Once editing is complete, the user clicks the "Final Confirm" button to finalize the storyboard.

[1848] Output: Edited and finalized storyboard.

[1849] (Application example 2)

[1850] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1851] In modern society, users' meal choices vary greatly depending on their mood and emotions on that day. However, conventional food delivery services lack the ability to recommend dishes that take the user's emotional state into account. As a result, it is difficult for users to achieve sufficient satisfaction when choosing a meal. In particular, there is a need for food recommendations that accurately reflect the user's emotions.

[1852] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1853] In this invention, the server includes means for receiving a plurality of pieces of prompt information input by the user, means for analyzing the prompt information and emotion data, means for selecting a generation algorithm based on the analysis results, means for analyzing the emotion information obtained from the emotion engine, means for recommending an optimal dish based on the prompt information and emotion information, and means for returning the recommended dish to the user, thereby enabling recipe suggestions that comprehensively consider the user's emotional state.

[1854] "User-entered prompt information" refers to a number of pieces of information entered by a user to embody a specific request or idea, including title, scene, action, location, food request, etc.

[1855] "Means for analyzing prompt information" refers to a processing function for analyzing the input prompt information in detail and understanding the user's intentions and goals.

[1856] The "means for selecting a generation algorithm" is a processing mechanism for determining an optimal generation algorithm based on the analyzed prompt information and emotion data.

[1857] The "means for generating a storyboard using a selected generation algorithm" is a function that uses a selected generation algorithm to automatically generate a storyboard that serves as a blueprint for a video or image.

[1858] The "means for returning the generated storyboard to the user" refers to a means for transmitting the generated storyboard to the user's terminal so that it can be displayed and edited.

[1859] "Means for displaying and editing the returned storyboard" refers to a function that allows the user to display the received storyboard on the terminal and edit or modify it as necessary.

[1860] The "emotion engine" is an analysis engine that analyzes the user's voice data, text data, and facial expression image data to identify the user's current emotional state.

[1861] "Means for integrating emotional information into analysis results" refers to a function that combines emotional information obtained from the emotion engine with the analysis results of prompt information to achieve comprehensive understanding.

[1862] The "means for recommending the most suitable dish" is a function for suggesting a dish that matches the user's emotional state and request based on the analyzed prompt information and emotional information.

[1863] The "means for returning recommended dishes to the user" refers to a means for sending information about the selected dishes to the user's terminal and suggesting them to the user.

[1864] The present invention relates to a food delivery application that recommends dishes taking into account the emotional state of the user. Specific embodiments for implementing the present invention will be described below.

[1865] System configuration

[1866] This system consists of an application that runs on the user's device, such as a smartphone or PC, and an emotion engine and generation algorithm that runs on the server side.

[1867] procedure

[1868] 1. User enters prompt

[1869] The user launches the application and enters their meal preference as a prompt, for example, a request such as "I would like something light."

[1870] 2. Emotion recognition by emotion engine

[1871] The device collects the user's voice data, text data, and facial expression image data when prompting, and sends them to the emotion engine, which analyzes this data and identifies the user's current emotional state.

[1872] 3. Sending prompt and emotional information

[1873] The device sends the prompt information and analyzed emotion data to the server, which then selects a generation algorithm based on this information.

[1874] 4. Food Recommendations

[1875] The server-side algorithm analyzes prompt and emotion information to recommend the most suitable dish. For example, if a user feels tired and wants to refresh, it will recommend cold soba noodles or a refreshing salad.

[1876] 5. Returning Recommendations

[1877] The server returns recommended dish information to the user's terminal, and the user can order dishes based on this information.

[1878] Hardware and software used

[1879] Hardware: Smartphones, PCs

[1880] Software: Sentiment analysis API (Python library), food delivery API

[1881] Data format: JSON format, text data, audio data, image data

[1882] Specific examples

[1883] For example, consider a case where a user feels tired and wants to relax. The user inputs into the app, "I'm tired, I want to relax. I want to eat something refreshing." The emotion engine analyzes the user's voice and facial expressions to determine that the user wants to relax. Based on the results of the analysis on the server side, recommendations such as "cold soba noodles" or "refreshing salad" are sent back to the user.

[1884] This allows users to easily order the food that best suits their emotional state at the time.

[1885] Examples of prompt statements include "I would like to eat something light," "I would like some spicy Chinese food," and "I would like to eat a special dessert."

[1886] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1887] Step 1:

[1888] A user launches the application and inputs a desired dish as a prompt. For example, the user may input "I want something light." The prompt information input by the user is collected in an input field of the application. The input data includes the user's request.

[1889] Step 2:

[1890] The device collects the user's voice data, text data, and facial expression image data. It prepares to send this data to the emotion engine. The collected data includes voice files (e.g., "I'm tired, I want to calm down"), text data, and image files (user's facial expressions).

[1891] Step 3:

[1892] The emotion engine analyzes the collected voice data, text data, and facial expression image data. From this data, the emotion engine identifies the user's current emotional state. Specifically, it uses voice analysis, text analysis, and image analysis algorithms to generate an emotional status, such as "I want to relax." The analysis results are output as emotional information.

[1893] Step 4:

[1894] The device sends prompt information and emotional information, which is the analysis result of the emotion engine, to the server. The sent data includes the user's cooking request (prompt information) and emotional data obtained through analysis, such as "I want to relax."

[1895] Step 5:

[1896] The server analyzes the prompt information and emotional information it receives. It uses natural language processing and facial expression analysis technologies to understand the user's input and emotions. Based on these results, it selects the optimal generation algorithm. For example, if the emotion is relaxed, it determines that a light dish would be appropriate. The input for the analysis is the prompt information and emotional data, and the output is the analysis result based on the selected algorithm.

[1897] Step 6:

[1898] The server uses a selected generation algorithm to recommend the best dish based on prompt and emotion information. During this generation process, dishes that match the criteria are extracted from a specific food database and selected as final candidates. The output includes dish candidates such as "cold soba noodles" and "refreshing salad."

[1899] Step 7:

[1900] The server sends the recommended dishes back to the user's device, which then displays the received dish information on the application's user interface. The user can then select from the dishes presented and confirm their order.

[1901] Step 8:

[1902] The user finally selects the food they want to order and confirms the order. By pressing the confirm button, the food ordering process is completed. The food selected by the user is sent as order data, and the food delivery service begins the process of delivering the food.

[1903] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1904] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1905] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1906] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1907] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1908] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1909] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1910] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1911] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1912] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1913] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1914] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1915] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1916] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1917] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1918] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1919] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1920] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1921] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1922] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1923] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1924] The following is further disclosed regarding the above embodiment.

[1925] (Claim 1)

[1926] means for receiving a plurality of prompt information input by a user;

[1927] means for analyzing the prompt information;

[1928] means for selecting a generation algorithm based on the analysis result;

[1929] means for generating a storyboard using the selected generation algorithm;

[1930] means for returning the generated storyboard to a user;

[1931] means for displaying and editing the returned storyboard;

[1932] A system including:

[1933] (Claim 2)

[1934] The system of claim 1 , wherein the prompt information includes a title, a scene, an action, and a location.

[1935] (Claim 3)

[1936] The system of claim 1, wherein the generation algorithm uses natural language processing and image generation techniques.

[1937] "Example 1"

[1938] (Claim 1)

[1939] means for receiving a plurality of prompt information input by a user;

[1940] means for analyzing the prompt information;

[1941] means for selecting a generation algorithm based on the analysis result;

[1942] means for generating a storyboard using the selected generation algorithm;

[1943] means for returning the generated storyboard to a user;

[1944] means for displaying and editing the returned storyboard;

[1945] means for transmitting prompt information from the user's terminal to the server;

[1946] A means for the server to analyze the prompt information using natural language processing technology;

[1947] A means for the server to select an optimal generation algorithm using natural language processing technology;

[1948] means for the server to generate a scene representation using a selected generation algorithm;

[1949] A means for the server to return the generated storyboard as an API response;

[1950] A system including:

[1951] (Claim 2)

[1952] The system of claim 1 , wherein the prompt information includes a title, a scene, an action, and a location.

[1953] (Claim 3)

[1954] The system of claim 1, wherein the generation algorithm uses natural language processing and image generation techniques.

[1955] "Application Example 1"

[1956] (Claim 1)

[1957] means for receiving a plurality of prompt information input by a user;

[1958] means for analyzing the prompt information;

[1959] means for selecting a generation algorithm based on the analysis result;

[1960] means for generating a storyboard using the selected generation algorithm;

[1961] means for returning the generated storyboard to a user;

[1962] means for displaying and editing the returned storyboard;

[1963] a means for sharing the generated storyboard with other users via a content sharing service;

[1964] A system including:

[1965] (Claim 2)

[1966] The system of claim 1 , wherein the prompt information includes a title, a scene, an action, and a location.

[1967] (Claim 3)

[1968] The system of claim 1, wherein the generation algorithm uses natural language processing and image generation techniques.

[1969] "Example 2: Combining Emotion Engines"

[1970] (Claim 1)

[1971] means for receiving a plurality of prompt information input by a user;

[1972] means for analyzing the prompt information;

[1973] means for selecting a generation algorithm based on the analysis result;

[1974] means for generating a storyboard using the selected generation algorithm;

[1975] means for returning the generated storyboard to a user;

[1976] means for displaying and editing the returned storyboard;

[1977] means for detecting a user's emotion and analyzing the emotion information together with the prompt information;

[1978] a means for including emotion-reflecting elements in a storyboard generated based on the analyzed emotion information;

[1979] A system including:

[1980] (Claim 2)

[1981] The system of claim 1 , wherein the prompt information includes a title, a scene, an action, and a location.

[1982] (Claim 3)

[1983] The system of claim 1, wherein the generation algorithm uses natural language processing and image generation techniques.

[1984] "Application example 2 when combining emotion engines"

[1985] (Claim 1)

[1986] means for receiving a plurality of prompt information input by a user;

[1987] means for analyzing the prompt information;

[1988] means for selecting a generation algorithm based on the analysis result;

[1989] means for generating a storyboard using the selected generation algorithm;

[1990] means for returning the generated storyboard to a user;

[1991] means for displaying and editing the returned storyboard;

[1992] An emotion engine that analyzes input emotion data;

[1993] means for integrating emotion information acquired by the emotion engine into an analysis result;

[1994] means for recommending an optimal dish based on the emotion information and prompt information;

[1995] means for returning the recommended dishes to the user;

[1996] A system including:

[1997] (Claim 2)

[1998] The system of claim 1 , wherein the prompt information includes a title, a scene, an action, a location, or a cooking request.

[1999] (Claim 3)

[2000] 2. The system according to claim 1, wherein the generation algorithm uses natural language processing and image generation techniques, and the emotion engine analyzes voice data, text data, and facial expression image data. [Explanation of symbols]

[2001] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving a plurality of prompt information input by a user; means for analyzing the prompt information; means for selecting a generation algorithm based on the analysis result; means for generating a storyboard using the selected generation algorithm; means for returning the generated storyboard to a user; means for displaying and editing the returned storyboard; A system including:

2. The system of claim 1 , wherein the prompt information includes a title, a scene, an action, and a location.

3. The system of claim 1 , wherein the generation algorithm uses natural language processing and image generation techniques.

Images